% !Mode:: "TeX:UTF-8"
% !TEX encoding = UTF-8 Unicode
new
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 1------------------------------------------------------
@book{慧立2000大慈恩寺三藏法師傳,
title={大慈恩寺三藏法師傳},
author={慧立 and 彦悰 and 道宣},
volume={2},
year={2000},
publisher={中华书局}
}
@book{2019cns,
title={2019中国语言服务行业发展报告},
author={中国翻译协会},
publisher={中国翻译协会},
year={2019}
}
@inproceedings{赵军峰2019深化改革,
title ={深化改革 探讨创新 推进发展——全国翻译专业学位研究生教育2019年会综述},
author ={赵军峰,姚恺璇},
publisher ={中国翻译},
year ={2019},
}
@book{knowlson1975universal,
title={Universal Language Schemes in England and France 1600-1800},
author={James {Knowlson}},
year={1975},
publisher={University of Toronto Press}
}
@inproceedings{DBLP:journals/bstj/Shannon48,
author = {Claude E. Shannon},
title = {A mathematical theory of communication},
publisher = {Bell System Technical Journal},
volume = {27},
number = {3},
pages = {379--423},
year = {1948}
}
@inproceedings{shannon1949the,
title={The mathematical theory of communication},
author={Claude E. {Shannon} and Warren {Weaver}},
publisher={IEEE Transactions on Instrumentation and Measurement},
volume={13},
year={1949}
}
@inproceedings{weaver1955translation,
title={Translation},
author={Weaver, Warren},
publisher={Machine translation of languages},
volume={14},
number={15-23},
pages={10},
year={1955},
publisher={Cambridge: Technology Press, MIT}
}
@inproceedings{chomsky1957syntactic,
title={Syntactic Structures},
author={Chomsky, Noam},
publisher={Language},
volume={33},
number={3},
year={1957},
}
@inproceedings{DBLP:conf/coling/SatoN90,
author = {Satoshi Sato and
Makoto Nagao},
title = {Toward Memory-based Translation},
publisher = {International Conference on Computational Linguistics},
pages = {247--252},
year = {1990}
}
@inproceedings{DBLP:journals/coling/BrownPPM94,
author = {Peter F. Brown and
Stephen Della Pietra and
Vincent J. Della Pietra and
Robert L. Mercer},
title = {The Mathematics of Statistical Machine Translation: Parameter Estimation},
publisher = {Computational Linguistics},
volume = {19},
number = {2},
pages = {263--311},
year = {1993}
}
@inproceedings{nirenburg1989knowledge,
title={Knowledge-based machine translation},
author={Nirenburg, Sergei},
publisher={Machine Translation},
volume={4},
number={1},
pages={5--24},
year={1989},
publisher={Springer}
}
@book{hutchins1986machine,
title={Machine translation: past, present, future},
author={Hutchins, William John},
year={1986},
publisher={Ellis Horwood Chichester}
}
@inproceedings{zarechnak1979history,
title={The history of machine translation},
author={Zarechnak, Michael},
publisher={Machine Translation},
volume={1979},
pages={1--87},
year={1979}
}
@book{冯志伟2004机器翻译研究,
title={机器翻译研究},
author={冯志伟},
publisher={中国对外翻译出版公司},
year={2004},
}
@inproceedings{王宝库1991机器翻译系统中一种规则描述语言,
title={机器翻译系统中一种规则描述语言(CTRDL)},
author={王宝库,张中义,姚天顺},
publisher={中文信息学报},
volume={5},
number={4},
year={1991},
}
@inproceedings{唐泓英1995基于搭配词典的词汇语义驱动算法,
title={基于搭配词典的词汇语义驱动算法},
author={唐泓英,姚天顺},
publisher={软件学报},
volume={6},
number={A01},
pages={78-85},
year={1995},
}
@inproceedings{nagao1984framework,
title={A framework of a mechanical translation between Japanese and English by analogy principle},
author={Nagao, Makoto},
publisher={Artificial and human intelligence},
pages={351--354},
year={1984}
}
@inproceedings{gale1993a,
title={A program for aligning sentences in bilingual corpora},
author={William A. {Gale} and Kenneth W. {Church}},
publisher={Computational Linguistics},
volume={19},
number={1},
pages={75--102},
year={1993}
}
@inproceedings{Wu2016GooglesNM,
author = {Yonghui Wu and
Mike Schuster and
Zhifeng Chen and
Quoc V. Le and
Mohammad Norouzi and
Wolfgang Macherey and
Maxim Krikun and
Yuan Cao and
Qin Gao and
Klaus Macherey and
Jeff Klingner and
Apurva Shah and
Melvin Johnson and
Xiaobing Liu and
Lukasz Kaiser and
Stephan Gouws and
Yoshikiyo Kato and
Taku Kudo and
Hideto Kazawa and
Keith Stevens and
George Kurian and
Nishant Patil and
Wei Wang and
Cliff Young and
Jason Smith and
Jason Riesa and
Alex Rudnick and
Oriol Vinyals and
Greg Corrado and
Macduff Hughes and
Jeffrey Dean},
title = {Google's Neural Machine Translation System: Bridging the Gap between
Human and Machine Translation},
publisher = {CoRR},
volume = {abs/1609.08144},
year = {2016}
}
@inproceedings{DBLP:journals/corr/LuongPM15,
author = {Thang Luong and
Hieu Pham and
Christopher D. Manning},
title = {Effective Approaches to Attention-based Neural Machine Translation},
publisher = {Conference on Empirical Methods in Natural
Language Processing},
pages = {1412--1421},
year = {2015}
}
@inproceedings{DBLP:journals/corr/GehringAGYD17,
author = {Jonas Gehring and
Michael Auli and
David Grangier and
Denis Yarats and
Yann N. Dauphin},
title = {Convolutional Sequence to Sequence Learning},
publisher = {International Conference on Machine Learning},
volume = {70},
pages = {1243--1252},
year = {2017}
}
@inproceedings{bahdanau2014neural,
author = {Dzmitry Bahdanau and
Kyunghyun Cho and
Yoshua Bengio},
title = {Neural Machine Translation by Jointly Learning to Align and Translate},
publisher = {International Conference on Learning Representations},
year = {2015}
}
@inproceedings{NIPS2014_5346,
author = {Ilya Sutskever and
Oriol Vinyals and
Quoc V. Le},
title = {Sequence to Sequence Learning with Neural Networks},
publisher = {Advances in Neural Information Processing Systems},
pages = {3104--3112},
year = {2014}
}
@book{koehn2009statistical,
author = {Philipp Koehn},
title = {Statistical Machine Translation},
publisher = {Cambridge University Press},
year = {2010}
}
@book{DBLP:journals/corr/abs-1709-07809,
author = {Philipp Koehn},
title = {Neural Machine Translation},
publisher = {Cambridge University Press},
year = {2020}
}
@book{宗成庆2013统计自然语言处理,
title ={统计自然语言处理},
author ={宗成庆},
year ={2013},
publisher ={清华大学出版社}
}
@book{Goodfellow-et-al-2016,
author = {Ian J. Goodfellow and
Yoshua Bengio and
Aaron C. Courville},
title = {Deep Learning},
publisher = {{MIT} Press},
year = {2016}
}
@inproceedings{goldberg2017neural,
title={Neural network methods for natural language processing},
author={Goldberg, Yoav},
publisher={Synthesis Lectures on Human Language Technologies},
volume={10},
number={1},
pages={1--309},
year={2017},
publisher={Morgan \& Claypool Publishers}
}
@book{周志华2016机器学习,
title ={机器学习},
author ={周志华},
year ={2016},
publisher ={清华大学出版社}
}
@book{李航2019统计学习方法,
title ={统计学习方法},
author ={李航},
year ={2019},
publisher ={清华大学出版社}
}
@book{邱锡鹏2020神经网络与深度学习,
title ={神经网络与深度学习},
author ={邱锡鹏},
publisher ={机械工业出版社},
year ={2020}
}
%%%%% chapter 1------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 2------------------------------------------------------
@book{kolmogorov2018foundations,
title ={Foundations of the theory of probability: Second English Edition},
author ={Kolmogorov, Andre Nikolaevich and Bharucha-Reid, Albert T},
year ={2018},
publisher ={Courier Dover Publications}
}
@book{mao-prob-book-2011,
title ={概率论与数理统计教程: 第二版},
author ={魏宗舒},
year ={2011},
publisher ={北京: 高等教育出版社}
}
@inproceedings{resnick1992adventures,
author = {Barbour, A. and Resnick, Sidney},
year = {1993},
month = {12},
pages = {1474},
title = {Adventures in Stochastic Processes.},
volume = {88},
publisher = {Journal of the American Statistical Association}
}
@book{liuke-markov-2004,
title ={实用马尔可夫决策过程},
author ={刘克},
year ={2004},
publisher ={清华大学出版社}
}
@inproceedings{gale1995good,
author = {William A. Gale and
Geoffrey Sampson},
title = {Good-Turing Frequency Estimation Without Tears},
publisher = {Journal of Quantitative Linguistics},
volume = {2},
number = {3},
pages = {217--237},
year = {1995}
}
@inproceedings{good1953population,
title ={The population frequencies of species and the estimation of population parameters},
author ={Good, Irving J},
publisher ={Biometrika},
volume ={40},
number ={3-4},
pages ={237--264},
year ={1953},
publisher ={Oxford University Press}
}
@inproceedings{kneser1995improved,
author = {Reinhard Kneser and
Hermann Ney},
title = {Improved backing-off for M-gram language modeling},
publisher = {International Conference on Acoustics, Speech, and Signal Processing},
pages = {181--184},
year = {1995}
}
@inproceedings{ney1991smoothing,
title={On smoothing techniques for bigram-based natural language modelling},
author={Ney, Hermann and Essen, Ute},
publisher={International Conference on Acoustics, Speech, and Signal Processing},
pages={825--828},
year={1991},
}
@inproceedings{stolcke2002srilm,
author = {Andreas Stolcke},
title = {{SRILM} - an extensible language modeling toolkit},
publisher = {International Conference on Spoken Language Processing},
year = {2002}
}
@inproceedings{chen1999empirical,
author = {Stanley F. Chen and
Joshua Goodman},
title = {An empirical study of smoothing techniques for language modeling},
publisher = {Computer Speech \& Language},
volume = {13},
number = {4},
pages = {359--393},
year = {1999}
}
@inproceedings{ney1994structuring,
author = {Hermann Ney and
Ute Essen and
Reinhard Kneser},
title = {On structuring probabilistic dependences in stochastic language modelling},
publisher = {Computer Speech \& Language},
volume = {8},
number = {1},
pages = {1--38},
year = {1994}
}
@book{parsing2009speech,
author = {Dan Jurafsky and
James H. Martin},
title = {Speech and language processing: an introduction to natural language
processing, computational linguistics, and speech recognition, 2nd
Edition},
publisher = {Prentice Hall, Pearson Education International},
year = {2009}
}
@book{DBLP:books/mg/CormenLR89,
author = {Thomas H. Cormen and
Charles E. Leiserson and
Ronald L. Rivest},
title = {Introduction to Algorithms},
publisher = {The {MIT} Press and McGraw-Hill Book Company},
year = {1989}
}
@book{even2011graph,
title={Graph algorithms},
author={Even, Shimon},
year={2011},
publisher={Cambridge University Press}
}
@inproceedings{tarjan1972depth,
title={Depth-First Search and Linear Graph Algorithms},
author={Robert Endre {Tarjan}},
publisher={SIAM Journal on Computing},
volume={1},
number={2},
pages={146--160},
year={1972}
}
@inproceedings{DBLP:journals/ai/SabharwalS11,
author = {Ashish Sabharwal and
Bart Selman},
title = {S. Russell, P. Norvig, Artificial Intelligence: {A} Modern Approach,
Third Edition},
publisher = {Artificial Intelligence},
volume = {175},
number = {5-6},
pages = {935--937},
year = {2011}
}
@book{sahni1978fundamentals,
title={Fundamentals of Computer Algorithms},
author={Sartaj {Sahni} and Ellis {Horowitz}},
year={1978},
publisher={Computer Science Press}
}
@inproceedings{hart1968a,
title={A Formal Basis for the Heuristic Determination of Minimum Cost Paths},
author={Peter E. {Hart} and Nils J. {Nilsson} and Bertram {Raphael}},
publisher={IEEE Transactions on Systems Science and Cybernetics},
volume={4},
number={2},
pages={100--107},
year={1968}
}
@book{lowerre1976the,
title={The HARPY speech recognition system},
author={Bruce T. {Lowerre}},
publisher={Carnegie Mellon University},
year={1976}
}
@book{bishop1995neural,
title={Neural networks for pattern recognition},
author={Christopher M. {Bishop}},
year={1995},
publisher={Oxford university press}
}
@inproceedings{åström1965optimal,
title={Optimal control of Markov processes with incomplete state information},
author={Karl Johan {Åström}},
publisher={Journal of Mathematical Analysis and Applications},
volume={10},
number={1},
pages={174--205},
year={1965}
}
@inproceedings{korf1990real,
title={Real-time heuristic search},
author={Richard E. {Korf}},
publisher={Artificial Intelligence},
volume={42},
number={2},
pages={189--211},
year={1990}
}
@inproceedings{DBLP:conf/emnlp/HuangZM17,
author = {Liang Huang and
Kai Zhao and
Mingbo Ma},
title = {When to Finish? Optimal Beam Search for Neural Text Generation (modulo
beam size)},
pages = {2134--2139},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/Yang0M18,
author = {Yilin Yang and
Liang Huang and
Mingbo Ma},
title = {Breaking the Beam Search Curse: {A} Study of (Re-)Scoring Methods
and Stopping Criteria for Neural Machine Translation},
pages = {3054--3059},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{jelinek1980interpolated,
title={Interpolated estimation of Markov source parameters from sparse data},
author={F. {Jelinek}},
publisher={Pattern Recognition in Practice},
pages={381--397},
year={1980}
}
@inproceedings{katz1987estimation,
title={Estimation of probabilities from sparse data for the language model component of a speech recognizer},
author={S. {Katz}},
publisher={IEEE Transactions on Acoustics, Speech, and Signal Processing},
volume={35},
number={3},
pages={400--401},
year={1987}
}
@inproceedings{witten1991the,
title={The zero-frequency problem: estimating the probabilities of novel events in adaptive text compression},
author={I.H. {Witten} and T.C. {Bell}},
publisher={IEEE Transactions on Information Theory},
volume={37},
number={4},
pages={1085--1094},
year={1991}
}
@book{bell1990text,
title={Text compression},
author={Timothy C. {Bell} and John G. {Cleary} and Ian H. {Witten}},
year={1990},
publisher={Prentice Hall}
}
@inproceedings{goodman2001a,
title={A bit of progress in language modeling},
author={Joshua T. {Goodman}},
publisher={Computer Speech \& Language},
volume={15},
number={4},
pages={403--434},
year={2001}
}
@inproceedings{kirchhoff2005improved,
title={Improved Language Modeling for Statistical Machine Translation},
author={Katrin {Kirchhoff} and Mei {Yang}},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={125--128},
year={2005}
}
@inproceedings{koehn2007factored,
title={Factored Translation Models},
author={Philipp {Koehn} and Hieu {Hoang}},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages={868--876},
year={2007}
}
@inproceedings{sarikaya2007joint,
title={Joint Morphological-Lexical Language Modeling for Machine Translation},
author={Ruhi {Sarikaya} and Yonggang {Deng}},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages={145--148},
year={2007}
}
@inproceedings{heafield2011kenlm,
title={KenLM: Faster and Smaller Language Model Queries},
author={Kenneth {Heafield}},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages={187--197},
year={2011}
}
@inproceedings{federico2006how,
title={How Many Bits Are Needed To Store Probabilities for Phrase-Based Translation?},
author={Marcello {Federico} and Nicola {Bertoldi}},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages={94--101},
year={2006}
}
@inproceedings{federico2007efficient,
title={Efficient Handling of N-gram Language Models for Statistical Machine Translation},
author={Marcello {Federico} and Mauro {Cettolo}},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages={88--95},
year={2007}
}
@inproceedings{talbot2007randomised,
title={Randomised Language Modelling for Statistical Machine Translation},
author={David {Talbot} and Miles {Osborne}},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages={512--519},
year={2007}
}
@inproceedings{talbot2007smoothed,
title={Smoothed Bloom Filter Language Models: Tera-Scale LMs on the Cheap},
author={David {Talbot} and Miles {Osborne}},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages={468--476},
year={2007}
}
@inproceedings{jing2019a,
title={A Survey on Neural Network Language Models.},
author={Kun {Jing} and Jungang {Xu}},
publisher={arXiv preprint arXiv:1906.03591},
year={2019}
}
@inproceedings{bengio2003a,
title={A neural probabilistic language model},
author={Yoshua {Bengio} and Réjean {Ducharme} and Pascal {Vincent} and Christian {Janvin}},
publisher={Journal of Machine Learning Research},
volume={3},
number={6},
pages={1137--1155},
year={2003}
}
@inproceedings{mikolov2010recurrent,
author = {Tomas Mikolov and
Martin Karafi{\'{a}}t and
Luk{\'{a}}s Burget and
Jan Cernock{\'{y}} and
Sanjeev Khudanpur},
title = {Recurrent neural network based language model},
pages = {1045--1048},
publisher = {International Speech Communication Association},
year = {2010}
}
@inproceedings{sundermeyer2012lstm,
author = {Martin Sundermeyer and
Ralf Schl{\"{u}}ter and
Hermann Ney},
title = {{LSTM} Neural Networks for Language Modeling},
pages = {194--197},
publisher = {International Speech Communication Association},
year = {2012}
}
@inproceedings{vaswani2017attention,
title={Attention is All You Need},
author={Ashish {Vaswani} and Noam {Shazeer} and Niki {Parmar} and Jakob {Uszkoreit} and Llion {Jones} and Aidan N. {Gomez} and Lukasz {Kaiser} and Illia {Polosukhin}},
publisher={International Conference on Neural Information Processing},
pages={5998--6008},
year={2017}
}
@inproceedings{tillmann1997a,
title={A DP-based Search Using Monotone Alignments in Statistical Translation},
author={Christoph {Tillmann} and Stephan {Vogel} and Hermann {Ney} and Alex {Zubiaga}},
publisher = {Morgan Kaufmann Publishers},
pages={289--296},
year={1997}
}
@inproceedings{DBLP:conf/acl/WangW97,
author = {Ye-Yi Wang and
Alex Waibel},
title = {Decoding Algorithm in Statistical Machine Translation},
pages = {366--372},
publisher = {Morgan Kaufmann Publishers},
year = {1997}
}
@inproceedings{DBLP:conf/acl/OchUN01,
author = {Franz Josef Och and
Nicola Ueffing and
Hermann Ney},
title = {An Efficient A* Search Algorithm for Statistical Machine Translation},
publisher = {Proceedings of the {ACL} Workshop on Data-Driven Methods in Machine
Translation},
year = {2001}
}
@inproceedings{germann2001fast,
title={Fast Decoding and Optimal Decoding for Machine Translation},
author={Ulrich {Germann} and Michael {Jahr} and Kevin {Knight} and Daniel {Marcu} and Kenji {Yamada}},
publisher = {Morgan Kaufmann Publishers},
pages={228--235},
year={2001}
}
@inproceedings{germann2003greedy,
title={Greedy decoding for statistical machine translation in almost linear time},
author={Ulrich {Germann}},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages={1--8},
year={2003}
}
@inproceedings{Koehn2007Moses,
author = {Philipp Koehn and
Hieu Hoang and
Alexandra Birch and
Chris Callison-Burch and
Marcello Federico and
Nicola Bertoldi and
Brooke Cowan and
Wade Shen and
Christine Moran and
Richard Zens and
Chris Dyer and
Ondrej Bojar and
Alexandra Constantin and
Evan Herbst},
title = {Moses: Open Source Toolkit for Statistical Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/amta/Koehn04,
author = {Philipp Koehn},
title = {Pharaoh: {A} Beam Search Decoder for Phrase-Based Statistical Machine
Translation Models},
volume = {3265},
pages = {115--124},
publisher = {Springer},
year = {2004}
}
@inproceedings{bangalore2001a,
title={A finite-state approach to machine translation},
author={S. {Bangalore} and G. {Riccardi}},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages={381--388},
year={2001}
}
@inproceedings{DBLP:journals/mt/BangaloreR02,
author = {Srinivas Bangalore and
Giuseppe Riccardi},
title = {Stochastic Finite-State Models for Spoken Language Machine Translation},
publisher = {Machine Translation},
volume = {17},
number = {3},
pages = {165--184},
year = {2002}
}
@inproceedings{venugopal2007an,
title={An Efficient Two-Pass Approach to Synchronous-CFG Driven Statistical MT},
author={Ashish {Venugopal} and Andreas {Zollmann} and Vogel {Stephan}},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages={500--507},
year={2007}
}
@inproceedings{zollmann2007the,
author = {Andreas Zollmann and
Ashish Venugopal and
Matthias Paulik and
Stephan Vogel},
title = {The Syntax Augmented {MT} {(SAMT)} System at the Shared Task for the
2007 {ACL} Workshop on Statistical Machine Translation},
pages = {216--219},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{liu2006tree,
author = {Yang Liu and
Qun Liu and
Shouxun Lin},
title = {Tree-to-String Alignment Template for Statistical Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{galley2006scalable,
author = {Michel Galley and
Jonathan Graehl and
Kevin Knight and
Daniel Marcu and
Steve DeNeefe and
Wei Wang and
Ignacio Thayer},
title = {Scalable Inference and Training of Context-Rich Syntactic Translation
Models},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{chiang2005a,
author = {David Chiang},
title = {A Hierarchical Phrase-Based Model for Statistical Machine Translation},
pages = {263--270},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2005}
}
%%%%% chapter 2------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 3------------------------------------------------------
@inproceedings{ng2002discriminative,
author = {Ng, Andrew Y and Jordan, Michael I},
title = {On Discriminative vs. Generative Classifiers: {A} comparison of logistic
regression and naive Bayes},
pages = {841--848},
publisher = {{MIT} Press},
year = {2001},
}
@inproceedings{huang2008coling,
author = {Huang, Liang},
title = {Coling 2008: Advanced Dynamic Programming in Computational Linguistics: Theory, Algorithms and Applications-Tutorial notes},
year = {2008},
publisher = {International Conference on Computational Linguistics},
}
@book{aho1972theory,
author = {Aho, Alfred V and
Ullman, Jeffrey D},
title = {The theory of parsing, translation, and compiling},
publisher = {Prentice-Hall Englewood Cliffs, NJ},
year = {1973},
}
@inproceedings{rau1991extracting,
title={Extracting company names from text},
author={Rau, Lisa F},
pages={29--30},
year={1991},
publisher={IEEE Conference on Artificial Intelligence Application},
}
@inproceedings{张小衡1997中文机构名称的识别与分析,
title={中文机构名称的识别与分析},
author={张小衡 and 王玲玲},
publisher={中文信息学报},
volume={11},
number={4},
pages={22-33},
year={1997},
}
@inproceedings{lample2016neural,
author = {Guillaume Lample and
Miguel Ballesteros and
Sandeep Subramanian and
Kazuya Kawakami and
Chris Dyer},
title = {Neural Architectures for Named Entity Recognition},
pages = {260--270},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016},
}
@inproceedings{Baum1966Statistical,
title={Statistical Inference for Probabilistic Functions of Finite State Markov Chains},
author={Baum, Leonard E and Petrie, Ted},
publisher={Annals of Mathematical Stats},
volume={37},
number={6},
pages={1554-1563},
year={1966},
}
@inproceedings{baum1970maximization,
title={A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains},
author={Baum, Leonard E and Petrie, Ted and Soules, George and Weiss, Norman},
publisher={Annals of Mathematical Stats},
volume={41},
number={1},
pages={164--171},
year={1970},
}
@inproceedings{1977Maximum,
title={Maximum likelihood from incomplete data via the EM algorithm},
author={Dempster, Arthur P and Laird, Nan M and Rubin, Donald B},
publisher={Journal of the Royal Statistical Society: Series B (Methodological)},
volume={39},
number={1},
pages={1--22},
year={1977}
}
@inproceedings{1967Error,
title={Error bounds for convolutional codes and an asymptotically optimum decoding algorithm},
author={Viterbi, Andrew},
publisher={IEEE Transactions on Information Theory},
volume={13},
number={2},
pages={260-269},
year={1967},
}
@inproceedings{harrington2013机器学习实战,
title={机器学习实战},
author={Harrington, Peter},
publisher={人民邮电出版社, 北京},
year={2013}
}
@inproceedings{brants-2000-tnt,
title = {TnT - {A} Statistical Part-of-Speech Tagger},
author = {Brants, Thorsten},
year = {2000},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {224--231},
}
@inproceedings{tsuruoka-tsujii-2005-chunk,
title = {Chunk Parsing Revisited},
author = {Yoshimasa Tsuruoka and
Jun'ichi Tsujii},
year = {2005},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {133--140},
}
@inproceedings{li-etal-2003-news-oriented,
title = {News-Oriented Automatic Chinese Keyword Indexing},
author = {Li, Sujian and
Wang, Houfeng and
Yu, Shiwen and
Xin, Chengsheng},
year = {2003},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {92--97},
}
@inproceedings{2015Bidirectional,
title={Bidirectional LSTM-CRF Models for Sequence Tagging},
author={ Huang, Zhiheng and Xu, Wei and Yu, Kai },
publisher={CoRR},
year={2015},
}
@inproceedings{chiu2016named,
title={Named entity recognition with bidirectional LSTM-CNNs},
author={Chiu, Jason PC and Nichols, Eric},
publisher={Transactions of the Association for Computational Linguistics},
volume={4},
pages={357--370},
year={2016},
publisher={MIT Press}
}
@inproceedings{vzukov2018named,
author = {Andrej Zukov Gregoric and
Yoram Bachrach and
Sam Coope},
title = {Named Entity Recognition With Parallel Recurrent Neural Networks},
pages = {69--74},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018},
}
@inproceedings{Li2020A,
title={A Survey on Deep Learning for Named Entity Recognition},
author={Li, Jing and Sun, Aixin and Han, Jianglei and Li, Chenliang},
publisher={IEEE Transactions on Knowledge and Data Engineering},
volume={PP},
number={99},
pages={1-1},
year={2020},
}
@inproceedings{devlin2019bert,
title={Bert: Pre-training of deep bidirectional transformers for language understanding},
author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
year={2019},
pages = {4171--4186},
publisher = {Annual Meeting of the Association for Computational Linguistics},
}
@inproceedings{conneau2019unsupervised,
author = {Alexis Conneau and
Kartikay Khandelwal and
Naman Goyal and
Vishrav Chaudhary and
Guillaume Wenzek and
Francisco Guzm{\'{a}}n and
Edouard Grave and
Myle Ott and
Luke Zettlemoyer and
Veselin Stoyanov},
title = {Unsupervised Cross-lingual Representation Learning at Scale},
pages = {8440--8451},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020},
}
@book{chomsky1993lectures,
title={Lectures on government and binding: The Pisa lectures},
author={Chomsky, Noam},
year={1993},
publisher={Walter de Gruyter}
}
@inproceedings{DBLP:conf/acl/SennrichHB16a,
author = {Rico Sennrich and
Barry Haddow and
Alexandra Birch},
title = {Neural Machine Translation of Rare Words with Subword Units},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016},
}
@inproceedings{刘挺1998最大概率分词问题及其解法,
title={最大概率分词问题及其解法},
author={刘挺 and 吴岩 and 王开铸},
publisher={哈尔滨工业大学学报},
number={06},
pages={37-41},
year={1998},
}
@inproceedings{丁洁2010基于最大概率分词算法的中文分词方法研究,
title={基于最大概率分词算法的中文分词方法研究},
author={丁洁},
publisher={科技信息},
number={21},
pages={I0075--I0075},
year={2010}
}
@book{1995University,
title = {University of Sheffield: Description of the LaSIE-II system as used for MUC-7},
author = {Kevin Humphreys and
Robert J. Gaizauskas and
Saliha Azzam and
Charles Huyck and
Brian Mitchell and
Hamish Cunningham and
Yorick Wilks},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {1995},
}
@inproceedings{krupka1998isoquest,
title={IsoQuest Inc.: Description of the NetOwl™ Extractor System as Used for MUC-7},
author={Krupka, George and Hausman, Kevin},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year={1998}
}
@inproceedings{DBLP:conf/muc/BlackRM98,
author = {Black, William J and Rinaldi, Fabio and Mowatt, David},
title = {{FACILE:} Description of the {NE} System Used for {MUC-7}},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {1998},
}
@inproceedings{1996Hidden,
title={Hidden Markov models.},
author={ Eddy, Sean R },
publisher={Current Opinion in Structural Biology},
volume={6},
number={3},
pages={361-5},
year={1996},
}
@inproceedings{lafferty2001conditional,
author = {John D. Lafferty and
Andrew McCallum and
Fernando C. N. Pereira},
title = {Conditional Random Fields: Probabilistic Models for Segmenting and
Labeling Sequence Data},
pages = {282--289},
publisher = {proceedings of the Eighteenth International Conference on Machine
Learning},
year = {2001},
}
@book{kapur1989maximum,
title={Maximum-entropy models in science and engineering},
author={Kapur, Jagat Narain},
year={1989},
publisher={John Wiley \& Sons}
}
@inproceedings{1998Support,
title={Support vector machines},
author={Hearst, Marti A. and Dumais, Susan T and Osuna, Edgar and Platt, John and Scholkopf, Bernhard},
publisher={IEEE Intelligent Systems \& Their Applications},
volume={13},
number={4},
pages={18-28},
year={1998},
}
@inproceedings{2011Natural,
title={Natural Language Processing (almost) from Scratch},
author={ Collobert, Ronan and Weston, Jason and Bottou, Léon and Karlen, Michael and Kavukcuoglu, Koray and Kuksa, Pavel },
publisher={Journal of Machine Learning Research},
volume={12},
number={1},
pages={2493-2537},
year={2011},
}
@book{manning2008introduction,
title={Introduction to information retrieval},
author={Manning, Christopher D and Sch{\"u}tze, Hinrich and Raghavan, Prabhakar},
year={2008},
publisher={Cambridge university press}
}
@inproceedings{berger1996maximum,
title={A maximum entropy approach to natural language processing},
author={Berger, Adam and Della Pietra, Stephen A and Della Pietra, Vincent J},
publisher={Computational linguistics},
volume={22},
number={1},
pages={39--71},
year={1996}
}
@book{mitchell1996m,
title={Machine Learning},
author={Mitchell, Tom},
publisher={McCraw Hill},
year={1996}
}
@inproceedings{DBLP:conf/acl/OchN02,
author = {Franz Josef Och and
Hermann Ney},
title = {Discriminative Training and Maximum Entropy Models for Statistical
Machine Translation},
pages = {295--302},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2002},
}
@incollection{mohri2008speech,
title={Speech recognition with weighted finite-state transducers},
author={Mohri, Mehryar and Pereira, Fernando and Riley, Michael},
pages={559--584},
year={2008},
publisher={Springer}
}
@inproceedings{bellman1966dynamic,
title={Dynamic programming},
author={Bellman, Richard},
publisher={Science},
volume={153},
number={3731},
pages={34--37},
year={1966}
}
%%%%% chapter 3------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 4------------------------------------------------------
@inproceedings{DBLP:conf/acl/PapineniRWZ02,
author = {Kishore Papineni and
Salim Roukos and
Todd Ward and
Wei-jing Zhu},
title = {Bleu: a Method for Automatic Evaluation of Machine Translation},
pages = {311--318},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2002}
}
@inproceedings{DBLP:journals/mt/ChurchH93,
title={Good applications for crummy machine translation},
author={Church, Kenneth W and Hovy, Eduard H},
volume={8},
number={4},
pages={239--258},
year={1993},
publisher={Springer}
}
@inproceedings{DBLP:conf/coling/SuWC92,
author = {Keh-Yih Su and
Ming-Wen Wu and
Jing-Shin Chang},
title = {A New Quantitative Quality Measure for Machine Translation Systems},
publisher = {International Conference on Computational Linguistics},
pages = {433--439},
year = {1992},
}
@inproceedings{DBLP:conf/interspeech/TillmannVNZS97,
title={Accelerated DP based search for statistical translation},
author={Tillmann, Christoph and Vogel, Stephan and Ney, Hermann and Zubiaga, Arkaitz and Sawaf, Hassan},
publisher={European Conference on Speech Communication and Technology},
year={1997}
}
@inproceedings{snover2006study,
title={A study of translation edit rate with targeted human annotation},
author={Snover, Matthew and Dorr, Bonnie and Schwartz, Richard and Micciulla, Linnea and Makhoul, John},
publisher={Proceedings of association for machine translation in the Americas},
volume={200},
number={6},
year={2006}
}
@inproceedings{DBLP:conf/muc/Chinchor92,
author = {Nancy Chinchor},
title = {{MUC-4} evaluation metrics},
pages = {22--29},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {1992}
}
@inproceedings{DBLP:conf/emnlp/ChiangDCN08,
author = {David Chiang and
Steve DeNeefe and
Yee Seng Chan and
Hwee Tou Ng},
title = {Decomposability of Translation Metrics for Improved Evaluation and
Efficient Algorithms},
pages = {610--619},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2008}
}
@inproceedings{DBLP:conf/acl/BanerjeeL05,
author = {Satanjeev Banerjee and
Alon Lavie},
title = {{METEOR:} An Automatic Metric for {MT} Evaluation with Improved Correlation
with Human Judgments},
pages = {65--72},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2005}
}
@inproceedings{DBLP:conf/wmt/DenkowskiL10,
author = {Michael J. Denkowski and
Alon Lavie},
title = {{METEOR-NEXT} and the {METEOR} Paraphrase Tables: Improved Evaluation
Support for Five Target Languages},
pages = {339--342},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2010}
}
@inproceedings{DBLP:conf/wmt/DenkowskiL11,
author = {Michael J. Denkowski and
Alon Lavie},
title = {Meteor 1.3: Automatic Metric for Reliable Optimization and Evaluation
of Machine Translation Systems},
pages = {85--91},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2011},
}
@inproceedings{DBLP:conf/wmt/DenkowskiL14,
author = {Michael J. Denkowski and
Alon Lavie},
title = {Meteor Universal: Language Specific Translation Evaluation for Any
Target Language},
pages = {376--380},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{DBLP:journals/mt/Shiwen93,
author = {Shiwen Yu},
title = {Automatic evaluation of output quality for Machine Translation systems},
publisher = {Mach. Transl.},
volume = {8},
number = {1-2},
pages = {117--126},
year = {1993}
}
@inproceedings{DBLP:conf/coling/ZhouWLLZZ08,
author = {Ming Zhou and
Bo Wang and
Shujie Liu and
Mu Li and
Dongdong Zhang and
Tiejun Zhao},
title = {Diagnostic Evaluation of Machine Translation Systems Using Automatically
Constructed Linguistic Check-Points},
publisher = {International Conference on Computational Linguistics},
pages = {1121--1128},
year = {2008}
}
@inproceedings{DBLP:conf/acl/AlbrechtH07a,
author = {Joshua Albrecht and
Rebecca Hwa},
title = {A Re-examination of Machine Learning Approaches for Sentence-Level
{MT} Evaluation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/acl/AlbrechtH07,
author = {Joshua Albrecht and
Rebecca Hwa},
title = {Regression for Sentence-Level {MT} Evaluation with Pseudo References},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/naacl/LiuG07,
author = {Ding Liu and
Daniel Gildea},
title = {Source-Language Features and Maximum Correlation Training for Machine
Translation Evaluation},
pages = {41--48},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/ijcnlp/GimenezM08,
author = {Jes{\'{u}}s Gim{\'{e}}nez and
Llu{\'{\i}}s M{\`{a}}rquez},
title = {Heterogeneous Automatic {MT} Evaluation Through Non-Parametric Metric
Combinations},
pages = {319--326},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2008}
}
@inproceedings{DBLP:conf/naacl/DreyerM12,
author = {Markus Dreyer and
Daniel Marcu},
title = {HyTER: Meaning-Equivalent Semantics for Translation Evaluation},
pages = {162--171},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2012}
}
@inproceedings{DBLP:conf/tsd/BojarMTZ13,
author = {Ondrej Bojar and
Matous Mach{\'{a}}cek and
Ales Tamchyna and
Daniel Zeman},
title = {Scratching the Surface of Possible Translations},
volume = {8082},
pages = {465--474},
publisher = {Springer},
year = {2013}
}
@inproceedings{DBLP:conf/eamt/QinS15,
author = {Ying Qin and
Lucia Specia},
title = {Truly Exploring Multiple References for Machine Translation Evaluation},
publisher = {European Association for Machine Translation},
year = {2015}
}
@inproceedings{DBLP:conf/emnlp/SocherPHNM11,
author = {Richard Socher and
Jeffrey Pennington and
Eric H. Huang and
Andrew Y. Ng and
Christopher D. Manning},
title = {Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions},
pages = {151--161},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2011}
}
@inproceedings{DBLP:conf/emnlp/SocherPWCMNP13,
author = {Richard Socher and
Alex Perelygin and
Jean Wu and
Jason Chuang and
Christopher D. Manning and
Andrew Y. Ng and
Christopher Potts},
title = {Recursive Deep Models for Semantic Compositionality Over a Sentiment
Treebank},
pages = {1631--1642},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013},
}
@inproceedings{DBLP:journals/corr/MatsuoKS17,
author = {Junki Matsuo and
Mamoru Komachi and
Katsuhito Sudoh},
title = {Word-Alignment-Based Segment-Level Machine Translation Evaluation
using Word Embeddings},
publisher = {CoRR},
volume = {abs/1704.00380},
year = {2017}
}
@inproceedings{DBLP:journals/csl/GuzmanJMN17,
title={Machine translation evaluation with neural networks},
author={Guzm{\'a}n, Francisco and Joty, Shafiq and M{\`a}rquez, Llu{\'\i}s and Nakov, Preslav},
publisher={Computer Speech \& Language},
volume={45},
pages={180--200},
year={2017}
}
@inproceedings{gamon2005sentence,
title={Sentence-level MT evaluation without reference translations: Beyond language modeling},
author={Gamon, Michael and Aue, Anthony and Smets, Martine},
publisher={Proceedings of EAMT},
pages={103--111},
year={2005}
}
@inproceedings{DBLP:conf/lrec/Quirk04,
author = {Christopher Quirk},
title = {Training a Sentence-Level Machine Translation Confidence Measure},
publisher = {European Language Resources Association},
year = {2004}
}
@inproceedings{DBLP:conf/icassp/JonesGSGHRW05,
author = {Douglas A. Jones and
Edward Gibson and
Wade Shen and
Neil Granoien and
Martha Herzog and
Douglas A. Reynolds and
Clifford J. Weinstein},
title = {Measuring human readability of machine generated text: three case
studies in speech recognition and machine translation},
pages = {1009--1012},
publisher = {{IEEE}},
year = {2005}
}
@inproceedings{DBLP:conf/eamt/ScartonZVGS15,
author = {Carolina Scarton and
Marcos Zampieri and
Mihaela Vela and
Josef van Genabith and
Lucia Specia},
title = {Searching for Context: a Study on Document-Level Labels for Translation
Quality Estimation},
publisher = {European Association for Machine Translation},
year = {2015}
}
@inproceedings{DBLP:conf/interspeech/FetterDR96,
title={Word graph rescoring using confidence measures},
author={Fetter, Pablo and Dandurand, Fr{\'e}d{\'e}ric and Regel-Brietzmann, Peter},
publisher={Proceeding of Fourth International Conference on Spoken Language Processing},
volume={1},
pages={10--13},
year={1996}
}
@inproceedings{DBLP:conf/acl/ShenCHHWSL16,
author = {Shiqi Shen and
Yong Cheng and
Zhongjun He and
Wei He and
Hua Wu and
Maosong Sun and
Yang Liu},
title = {Minimum Risk Training for Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016},
}
@inproceedings{DBLP:conf/wmt/FreitagCR19,
author = {Markus Freitag and
Isaac Caswell and
Scott Roy},
title = {{APE} at Scale and Its Implications on {MT} Evaluation Biases},
pages = {34--44},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:journals/mt/BiciciGG13,
title={Predicting sentence translation quality using extrinsic and language independent features},
author={Bi{\c{c}}ici, Ergun and Groves, Declan and van Genabith, Josef},
publisher={Machine Translation},
volume={27},
number={3-4},
pages={171--192},
year={2013}
}
@inproceedings{DBLP:conf/wmt/BiciciW14,
author = {Ergun Bi{\c{c}}ici and
Andy Way},
title = {Referential Translation Machines for Predicting Translation Quality},
pages = {313--321},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/wmt/BiciciLW15a,
author = {Ergun Bi{\c{c}}ici and
Qun Liu and
Andy Way},
title = {Referential Translation Machines for Predicting Translation Quality
and Related Statistics},
pages = {304--308},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:conf/iclr/LogeswaranL18,
author = {Lajanugen Logeswaran and
Honglak Lee},
title = {An efficient framework for learning sentence representations},
publisher = {OpenReview.net},
year = {2018}
}
@inproceedings{iyyer-etal-2015-deep,
title = {Deep Unordered Composition Rivals Syntactic Methods for Text Classification},
author = {Iyyer, Mohit and
Manjunatha, Varun and
Boyd-Graber, Jordan and
Daum{\'e} III, Hal},
month = jul,
year = {2015},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {1681--1691},
}
@inproceedings{DBLP:journals/corr/abs-1301-3781,
author = {Tomas Mikolov and
Kai Chen and
Greg Corrado and
Jeffrey Dean},
title = {Efficient Estimation of Word Representations in Vector Space},
publisher = {arXiv preprint arXiv:1301.3781},
year = {2013}
}
@inproceedings{DBLP:conf/icml/LeM14,
title={Distributed representations of sentences and documents},
author={Le, Quoc and Mikolov, Tomas},
publisher={International conference on machine learning},
pages={1188--1196},
year={2014}
}
@inproceedings{DBLP:conf/acl/AthiwaratkunW17,
author = {Ben Athiwaratkun and
Andrew Gordon Wilson},
title = {Multimodal Word Distributions},
pages = {1645--1656},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/PenningtonSM14,
author = {Jeffrey Pennington and
Richard Socher and
Christopher D. Manning},
title = {Glove: Global Vectors for Word Representation},
pages = {1532--1543},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/nips/KirosZSZUTF15,
title={Skip-thought vectors},
author={Kiros, Ryan and Zhu, Yukun and Salakhutdinov, Russ R and Zemel, Richard and Urtasun, Raquel and Torralba, Antonio and Fidler, Sanja},
publisher={Advances in neural information processing systems},
pages={3294--3302},
year={2015}
}
@inproceedings{radford2018improving,
title={Improving language understanding by generative pre-training},
author={Radford, Alec and Narasimhan, Karthik and Salimans, Tim and Sutskever, Ilya},
year={2018}
}
@inproceedings{DBLP:journals/mtcl/Carroll66,
author = {John B. Carroll},
title = {An experiment in evaluating the quality of translations},
publisher = {Mech. Transl. Comput. Linguistics},
volume = {9},
number = {3-4},
pages = {55--66},
year = {1966}
}
@inproceedings{DBLP:conf/amta/WhiteOO94,
title={The ARPA MT evaluation methodologies: evolution, lessons, and future approaches},
author={White, John S and O’Connell, Theresa A and O’Mara, Francis E},
publisher={Proceedings of the First Conference of the Association for Machine Translation in the Americas},
year={1994}
}
@inproceedings{king2003femti,
title={FEMTI: creating and using a framework for MT evaluation},
author={King, Margaret and Popescu-Belis, Andrei and Hovy, Eduard},
publisher={Proceedings of MT Summit IX, New Orleans, LA},
pages={224--231},
year={2003}
}
@inproceedings{DBLP:journals/mt/PrzybockiPBS09,
author = {Mark A. Przybocki and
Kay Peterson and
Sebastien Bronsart and
Gregory A. Sanders},
title = {The {NIST} 2008 Metrics for machine translation challenge - overview,
methodology, metrics, and results},
publisher = {Machine Translation},
volume = {23},
number = {2-3},
pages = {71--103},
year = {2009}
}
@inproceedings{reeder2006direct,
title={Direct application of a language learner test to MT evaluation},
author={Reeder, Florence},
publisher={Proceedings of AMTA},
year={2006}
}
@inproceedings{DBLP:conf/wmt/Callison-BurchF07,
author = {Chris Callison-Burch and
Cameron S. Fordyce and
Philipp Koehn and
Christof Monz and
Josh Schroeder},
title = {(Meta-) Evaluation of Machine Translation},
pages = {136--158},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/wmt/Callison-BurchK12,
author = {Chris Callison-Burch and
Philipp Koehn and
Christof Monz and
Matt Post and
Radu Soricut and
Lucia Specia},
title = {Findings of the 2012 Workshop on Statistical Machine Translation},
pages = {10--51},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2012}
}
@inproceedings{DBLP:conf/wmt/Lopez12,
author = {Adam Lopez},
title = {Putting Human Assessments of Machine Translation Systems in Order},
pages = {1--9},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2012}
}
@inproceedings{DBLP:conf/wmt/BojarCFHHHKLMNP15,
author = {Ondrej Bojar and
Rajen Chatterjee and
Christian Federmann and
Barry Haddow and
Matthias Huck and
Chris Hokamp and
Philipp Koehn and
Varvara Logacheva and
Christof Monz and
Matteo Negri and
Matt Post and
Carolina Scarton and
Lucia Specia and
Marco Turchi},
title = {Findings of the 2015 Workshop on Statistical Machine Translation},
pages = {1--46},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:conf/iwslt/Koehn12,
author = {Philipp Koehn},
title = {Simulating human judgment in machine translation evaluation campaigns},
pages = {179--184},
publisher = {International Workshop on Spoken Language Translation},
year = {2012}
}
@inproceedings{DBLP:conf/acl/LiuG05,
author = {Ding Liu and
Daniel Gildea},
title = {Syntactic Features for Evaluation of Machine Translation},
pages = {25--32},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2005}
}
@inproceedings{DBLP:conf/wmt/GimenezM07a,
author = {Jes{\'{u}}s Gim{\'{e}}nez and
Llu{\'{\i}}s M{\`{a}}rquez},
title = {Linguistic Features for Automatic Evaluation of Heterogenous {MT}
Systems},
pages = {256--264},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:journals/mt/PadoCGJM09,
author = {Sebastian Pad{\'{o}} and
Daniel M. Cer and
Michel Galley and
Dan Jurafsky and
Christopher D. Manning},
title = {Measuring machine translation quality as semantic equivalence: {A}
metric based on entailment features},
publisher = {Machine Translation},
volume = {23},
number = {2-3},
pages = {181--193},
year = {2009}
}
@inproceedings{DBLP:conf/ssst/OwczarzakGW07,
author = {Karolina Owczarzak and
Josef van Genabith and
Andy Way},
title = {Dependency-Based Automatic Evaluation for Machine Translation},
pages = {80--87},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007},
}
@inproceedings{DBLP:conf/wmt/OwczarzakGW07,
author = {Karolina Owczarzak and
Josef van Genabith and
Andy Way},
title = {Labelled Dependencies in Machine Translation Evaluation},
pages = {104--111},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007},
}
@inproceedings{DBLP:conf/coling/YuWXJLL14,
author = {Hui Yu and
Xiaofeng Wu and
Jun Xie and
Wenbin Jiang and
Qun Liu and
Shouxun Lin},
title = {{RED:} {A} Reference Dependency Based {MT} Evaluation Metric},
pages = {2042--2051},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/wmt/PopovicN09,
author = {Maja Popovic and
Hermann Ney},
title = {Syntax-Oriented Evaluation Measures for Machine Translation Output},
pages = {29--32},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{DBLP:conf/acl/BanchsL11,
author = {Rafael E. Banchs and
Haizhou Li},
title = {{AM-FM:} {A} Semantic Framework for Translation Quality Assessment},
pages = {153--158},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2011}
}
@inproceedings{reeder2006measuring,
title={Measuring MT adequacy using latent semantic analysis},
author={Reeder, Florence},
publisher={Proceedings of the 7th Conference of the Association for Machine Translation of the Americas. Cambridge, Massachusetts},
pages={176--184},
year={2006}
}
@inproceedings{DBLP:conf/acl/LoBSW14,
author = {Chi-kiu Lo and
Meriem Beloucif and
Markus Saers and
Dekai Wu},
title = {{XMEANT:} Better semantic {MT} evaluation without reference translations},
pages = {765--771},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/lrec/VilarXDN06,
author = {David Vilar and
Jia Xu and
Luis Fernando D'Haro and
Hermann Ney},
title = {Error Analysis of Statistical Machine Translation Output},
pages = {697--702},
publisher = {European Language Resources Association {(ELRA)}},
year = {2006}
}
@inproceedings{popovic2011human,
title={From human to automatic error classification for machine translation output},
author={Popovic, Maja and Burchardt, Aljoscha and others},
publisher={European Association for Machine Translation},
year={2011}
}
@inproceedings{DBLP:journals/mt/CostaLLCC15,
author = {{\^{A}}ngela Costa and
Wang Ling and
Tiago Lu{\'{\i}}s and
Rui Correia and
Lu{\'{\i}}sa Coheur},
title = {A linguistically motivated taxonomy for Machine Translation error
analysis},
publisher = {Machine Translation},
volume = {29},
number = {2},
pages = {127--161},
year = {2015}
}
@inproceedings{lommel2014using,
title={Using a new analytic measure for the annotation and analysis of MT errors on real data},
author={Lommel, Arle and Burchardt, Aljoscha and Popovic, Maja and Harris, Kim and Avramidis, Eleftherios and Uszkoreit, Hans},
publisher={European Association for Machine Translation},
pages={165--172},
year={2014}
}
@inproceedings{DBLP:conf/wmt/PopovicGGLNMFB06,
author = {Maja Popovic and
Adri{\`{a}} de Gispert and
Deepa Gupta and
Patrik Lambert and
Hermann Ney and
Jos{\'{e}} B. Mari{\~{n}}o and
Marcello Federico and
Rafael E. Banchs},
title = {Morpho-syntactic Information for Automatic Error Analysis of Statistical
Machine Translation Output},
pages = {1--6},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{DBLP:conf/wmt/PopovicN07,
author = {Maja Popovic and
Hermann Ney},
title = {Word Error Rates: Decomposition over {POS} classes and Applications
for Error Analysis},
pages = {48--55},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/acl/GonzalezMM13,
author = {Meritxell Gonz{\'{a}}lez and
Laura Mascarell and
Llu{\'{\i}}s M{\`{a}}rquez},
title = {tSEARCH: Flexible and Fast Search over Automatic Translations for
Improved Quality/Error Analysis},
pages = {181--186},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@inproceedings{coughlin2003correlating,
title={Correlating automated and human assessments of machine translation quality},
author={Coughlin, Deborah},
year={2003}
}
@inproceedings{popescu2003experiment,
title={An experiment in comparative evaluation: humans vs. computers},
author={Popescu-Belis, Andrei},
publisher={Proceedings of the Ninth Machine Translation Summit. New Orleans},
year={2003}
}
@inproceedings{pearson1920notes,
title={Notes on the history of correlation},
author={Pearson, Karl},
publisher={Biometrika},
volume={13},
number={1},
pages={25--45},
year={1920},
publisher={JSTOR}
}
@inproceedings{culy2003limits,
title={The limits of N-gram translation evaluation metrics},
author={Culy, Christopher and Riehemann, Susanne Z},
publisher={MT Summit IX},
pages={71--78},
year={2003}
}
@inproceedings{finch2004using,
title={Using a paraphraser to improve machine translation evaluation},
author={Finch, Andrew and Akiba, Yasuhiro and Sumita, Eiichiro},
publisher={International Joint Conference on Natural Language Processing},
year={2004}
}
@inproceedings{DBLP:conf/coling/HamonM08,
author = {Olivier Hamon and
Djamel Mostefa},
title = {The Impact of Reference Quality on Automatic {MT} Evaluation},
publisher = {International conference on machine learning},
pages = {39--42},
year = {2008}
}
@inproceedings{doddington2002automatic,
title={Automatic evaluation of machine translation quality using n-gram co-occurrence statistics},
publisher={Proceedings of the second international conference on Human Language Technology Research},
author={Doddington, George},
pages={138--145},
year={2002}
}
@inproceedings{callison2006re,
title={Re-evaluation the role of bleu in machine translation research},
author={Callison-Burch, Chris and Osborne, Miles and Koehn, Philipp},
publisher={11th Conference of the European Chapter of the Association for Computational Linguistics},
year={2006}
}
@InProceedings{Miller:2005:MTS,
author = {Keith J. Miller and Michelle Vanni},
title = {Inter-rater Agreement Measures, and the Refinement of Metrics in the PLATO MT Evaluation Paradigm},
publisher = {The tenth Machine Translation Summit},
pages = {125--132},
year = {2005}
}
@inproceedings{DBLP:conf/acl/Och03,
author = {Franz Josef Och},
title = {Minimum Error Rate Training in Statistical Machine Translation},
pages = {160--167},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2003},
}
@inproceedings{DBLP:conf/wmt/Post18,
author = {Matt Post},
title = {A Call for Clarity in Reporting {BLEU} Scores},
pages = {186--191},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018},
}
@inproceedings{he2012maximum,
title={Maximum expected bleu training of phrase and lexicon translation models},
author={He, Xiaodong and Deng, Li},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={292--301},
year={2012}
}
@inproceedings{DBLP:conf/acl/ChenG15,
author = {Boxing Chen and
Hongyu Guo},
title = {Representation Based Translation Evaluation Metrics},
pages = {150--155},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015},
}
@inproceedings{kulesza2004learning,
title={A learning approach to improving sentence-level MT evaluation},
author={Kulesza, Alex and Shieber, Stuart},
publisher={Proceedings of the 10th International Conference on Theoretical and Methodological Issues in Machine Translation},
year={2004}
}
@inproceedings{corston2001machine,
title={A machine learning approach to the automatic evaluation of machine translation},
author={Corston-Oliver, Simon and Gamon, Michael and Brockett, Chris},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={148--155},
year={2001}
}
@inproceedings{albrecht2008regression,
title={Regression for machine translation evaluation at the sentence level},
author={Albrecht, Joshua S and Hwa, Rebecca},
volume={22},
number={1-2},
pages={1},
year={2008},
publisher={Springer}
}
@inproceedings{duh2008ranking,
title={Ranking vs. regression in machine translation evaluation},
author={Duh, Kevin},
publisher={Proceedings of the Third Workshop on Statistical Machine Translation},
pages={191--194},
year={2008}
}
@inproceedings{chen2015multi,
title={Multi-level evaluation for machine translation},
author={Chen, Boxing and Guo, Hongyu and Kuhn, Roland},
publisher={Proceedings of the Tenth Workshop on Statistical Machine Translation},
pages={361--365},
year={2015}
}
@book{DBLP:books/sp/EfronT93,
author = {Bradley Efron and
Robert Tibshirani},
title = {An Introduction to the Bootstrap},
publisher = {Springer},
year = {1993}
}
@inproceedings{DBLP:conf/emnlp/Koehn04,
author = {Philipp Koehn},
title = {Statistical Significance Tests for Machine Translation Evaluation},
pages = {388--395},
publisher = {{ACL}},
year = {2004}
}
@book{noreen1989computer,
title={Computer-intensive methods for testing hypotheses},
author={Noreen, Eric W},
year={1989},
publisher={Wiley New York}
}
@inproceedings{DBLP:conf/acl/RiezlerM05,
author = {Stefan Riezler and
John T. Maxwell III},
title = {On Some Pitfalls in Automatic Evaluation and Significance Testing
for {MT}},
pages = {57--64},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2005}
}
@inproceedings{DBLP:conf/emnlp/Berg-KirkpatrickBK12,
author = {Taylor Berg-Kirkpatrick and
David Burkett and
Dan Klein},
title = {An Empirical Investigation of Statistical Significance in {NLP}},
pages = {995--1005},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2012}
}
@inproceedings{DBLP:conf/wmt/Bicici13a,
author = {Ergun Bi{\c{c}}ici},
title = {Referential Translation Machines for Quality Estimation},
pages = {343--351},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@inproceedings{DBLP:conf/wmt/SouzaBTN13,
author = {Jos{\'{e}} Guilherme Camargo de Souza and
Christian Buck and
Marco Turchi and
Matteo Negri},
title = {FBK-UEdin Participation to the {WMT13} Quality Estimation Shared Task},
pages = {352--358},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@inproceedings{DBLP:conf/wmt/SouzaGBTN14,
author = {Jos{\'{e}} Guilherme Camargo de Souza and
Jes{\'{u}}s Gonz{\'{a}}lez-Rubio and
Christian Buck and
Marco Turchi and
Matteo Negri},
title = {FBK-UPV-UEdin participation in the {WMT14} Quality Estimation shared-task},
pages = {322--328},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/wmt/Espla-GomisSF15,
author = {Miquel Espl{\`{a}}-Gomis and
Felipe S{\'{a}}nchez-Mart{\'{\i}}nez and
Mikel L. Forcada},
title = {UAlacant word-level machine translation quality estimation system
at {WMT} 2015},
pages = {309--315},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:conf/wmt/KreutzerSR15,
author = {Julia Kreutzer and
Shigehiko Schamoni and
Stefan Riezler},
title = {QUality Estimation from ScraTCH {(QUETCH):} Deep Learning for Word-level
Translation Quality Estimation},
pages = {316--322},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:conf/wmt/MartinsAHK16,
author = {Andr{\'{e}} F. T. Martins and
Ram{\'{o}}n Fern{\'{a}}ndez Astudillo and
Chris Hokamp and
Fabio Kepler},
title = {Unbabel's Participation in the {WMT16} Word-Level Translation Quality
Estimation Shared Task},
pages = {806--811},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/wmt/ChenTZXZLW17,
author = {Zhiming Chen and
Yiming Tan and
Chenlin Zhang and
Qingyu Xiang and
Lilin Zhang and
Maoxi Li and
Mingwen Wang},
title = {Improving Machine Translation Quality Estimation with Neural Network
Features},
pages = {551--555},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{kreutzer2015quality,
title={Quality estimation from scratch (quetch): Deep learning for word-level translation quality estimation},
author={Kreutzer, Julia and Schamoni, Shigehiko and Riezler, Stefan},
publisher={Proceedings of the Tenth Workshop on Statistical Machine Translation},
pages={316--322},
year={2015}
}
@inproceedings{DBLP:conf/wmt/ScartonBSSS16,
author = {Carolina Scarton and
Daniel Beck and
Kashif Shah and
Karin Sim Smith and
Lucia Specia},
title = {Word embeddings and discourse information for Quality Estimation},
pages = {831--837},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/wmt/AbdelsalamBE16,
author = {Amal Abdelsalam and
Ondrej Bojar and
Samhaa El-Beltagy},
title = {Bilingual Embeddings and Word Alignments for Translation Quality Estimation},
pages = {764--771},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/wmt/BasuPN18,
author = {Prasenjit Basu and
Santanu Pal and
Sudip Kumar Naskar},
title = {Keep It or Not: Word Level Quality Estimation for Post-Editing},
pages = {759--764},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/wmt/Lo19,
author = {Chi-kiu Lo},
title = {YiSi - a Unified Semantic {MT} Quality Evaluation and Estimation Metric
for Languages with Different Levels of Available Resources},
pages = {507--513},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/wmt/YankovskayaTF19,
author = {Elizaveta Yankovskaya and
Andre T{\"{a}}ttar and
Mark Fishel},
title = {Quality Estimation and Translation Metrics via Pre-trained Word and
Sentence Embeddings},
pages = {101--105},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/wmt/Qi19,
author = {Hou Qi},
title = {{NJU} Submissions for the {WMT19} Quality Estimation Shared Task},
pages = {95--100},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/wmt/ZhouZH19,
author = {Junpei Zhou and
Zhisong Zhang and
Zecong Hu},
title = {{SOURCE:} SOURce-Conditional Elmo-style Model for Machine Translation
Quality Estimation},
pages = {106--111},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/wmt/Hokamp17,
author = {Chris Hokamp},
title = {Ensembling Factored Neural Machine Translation Models for Automatic
Post-Editing and Quality Estimation},
pages = {647--654},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/wmt/KimLKN19,
author = {Hyun Kim and
Joon-Ho Lim and
Hyun-Ki Kim and
Seung-Hoon Na},
title = {{QE} {BERT:} Bilingual {BERT} Using Multi-task Learning for Neural
Quality Estimation},
pages = {85--89},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/wmt/HildebrandV13,
author = {Silja Hildebrand and
Stephan Vogel},
title = {{MT} Quality Estimation: The {CMU} System for WMT'13},
pages = {373--379},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@inproceedings{kepler2019unbabel,
title={Unbabel's Participation in the WMT19 Translation Quality Estimation Shared Task},
pages={78--84},
author={Kepler, F{\'a}bio and Tr{\'e}nous, Jonay and Treviso, Marcos and Vera, Miguel and G{\'o}is, Ant{\'o}nio and Farajian, M Amin and Lopes, Ant{\'o}nio V and Martins, Andr{\'e} FT},
year={2019}
}
@inproceedings{martins2016unbabel,
title={Unbabel’s participation in the wmt16 word-level translation quality estimation shared task},
author={Martins, Andr{\'e} FT and Astudillo, Ram{\'o}n and Hokamp, Chris and Kepler, Fabio},
publisher={Proceedings of the First Conference on Machine Translation},
pages={806--811},
year={2016}
}
@inproceedings{DBLP:conf/wmt/ShahLPBBBS15,
author = {Kashif Shah and
Varvara Logacheva and
Gustavo Paetzold and
Fr{\'{e}}d{\'{e}}ric Blain and
Daniel Beck and
Fethi Bougares and
Lucia Specia},
title = {{SHEF-NN:} Translation Quality Estimation with Neural Networks},
pages = {342--347},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@book{huang2019machine,
title={Machine Translation: 15th China Conference, CCMT 2019, Nanchang, China, September 27--29, 2019, Revised Selected Papers},
author={Huang, Shujian and Knight, Kevin},
volume={1104},
year={2019},
publisher={Springer Nature}
}
@inproceedings{akaike1974new,
title={A new look at the statistical model identification},
author={Akaike, Hirotugu},
volume={19},
number={6},
pages={716--723},
year={1974},
publisher={IEEE}
}
@inproceedings{wang2019niutrans,
title={NiuTrans Submission for CCMT19 Quality Estimation Task},
author={Wang, Ziyang and Liu, Hui and Chen, Hexuan and Feng, Kai and Wang, Zeyang and Li, Bei and Xu, Chen and Xiao, Tong and Zhu, Jingbo},
pages={82--92},
year={2019},
publisher={Springer}
}
@book{jurafsky2000speech,
title={Speech \& language processing},
author={Jurafsky, Dan},
year={2000},
publisher={Pearson Education India}
}
%%%%% chapter 4------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 5------------------------------------------------------
@inproceedings{brown1990statistical,
author = {Peter F. Brown and
John Cocke and
Stephen Della Pietra and
Vincent J. Della Pietra and
Frederick Jelinek and
John D. Lafferty and
Robert L. Mercer and
Paul S. Roossin},
title = {A Statistical Approach to Machine Translation},
publisher = {Computational Linguistics},
volume = {16},
number = {2},
pages = {79--85},
year = {1990}
}
@inproceedings{knight1999decoding,
author = {Kevin Knight},
title = {Decoding Complexity in Word-Replacement Translation Models},
publisher = {Computational Linguistics},
volume = {25},
number = {4},
pages = {607--615},
year = {1999}
}
@inproceedings{shannon1949communication,
title ={Communication theory of secrecy systems},
author ={Claude Elwood Shannon},
publisher ={Bell system technical journal},
volume ={28},
number ={4},
pages ={656--715},
year ={1949}
}
@inproceedings{DBLP:conf/acl/Moore04,
author = {Robert C. Moore},
title = {Improving {IBM} Word Alignment Model 1},
pages = {518--525},
publisher = {Annual Meeting of the Association for Computational
Linguistics},
year = {2004}
}
@inproceedings{肖桐1991面向统计机器翻译的重对齐方法研究,
title={面向统计机器翻译的重对齐方法研究},
author={肖桐 and
李天宁 and
陈如山 and
朱靖波 and
王会珍},
publisher ={中文信息学报},
volume={24},
number={110--116},
year={2010},
}
@inproceedings{2005Improvin,
author = {Hua Wu and
Haifeng Wang},
title = {Improving Statistical Word Alignment with Ensemble Methods},
volume = {3651},
pages = {462--473},
publisher = {International Joint Conference on Natural Language Processing},
year = {2005}
}
@inproceedings{1998Grammar,
title={Grammar Inference and Statistical Machine Translation},
author={Ye-Yi Wang and Wayne Ward},
year={1999},
publisher={Carnegie Mellon University}
}
@inproceedings{DBLP:conf/acl-vlc/DaganCG93,
author = {Ido Dagan and
Kenneth Ward Church and
Willian Gale},
title = {Robust Bilingual Word Alignment for Machine Aided Translation},
publisher = {Very Large Corpora},
year = {1993}
}
@inproceedings{DBLP:conf/naacl/GaleC91,
author = {William A. Gale and
Kenneth Ward Church},
title = {Identifying Word Correspondences in Parallel Texts},
publisher = {Morgan Kaufmann},
year = {1991}
}
@inproceedings{DBLP:conf/naacl/LiangTK06,
author = {Percy Liang and
Benjamin Taskar and
Dan Klein},
title = {Alignment by Agreement},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{DBLP:conf/naacl/DyerCS13,
author = {Chris Dyer and
Victor Chahuneau and
Noah A. Smith},
title = {A Simple, Fast, and Effective Reparameterization of {IBM} Model 2},
pages = {644--648},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@inproceedings{DBLP:conf/acl/DeNeroK07,
author = {John DeNero and
Dan Klein},
title = {Tailoring Word Alignments to Syntactic Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{paul2007all,
author = {Paul C Davis，Zhuli Xie and
Kevin Small},
publisher={Machine Translation Summit XI},
title = {All Links are not the Same: Evaluating Word Alignments for Statistical Machine Translation},
year = {2007}
}
@inproceedings{黄书剑2009一种错误敏感的词对齐评价方法,
title={一种错误敏感的词对齐评价方法},
author={黄书剑 and
奚宁 and
赵迎功 and
戴新宇 and
陈家骏},
publisher ={中文信息学报},
volume={23},
number={88-94},
year={2009}
}
@inproceedings{DBLP:journals/coling/FraserM07,
author = {Alexander Fraser and
Daniel Marcu},
title = {Measuring Word Alignment Quality for Statistical Machine Translation},
publisher = {Computational Linguistics},
volume = {33},
number = {3},
pages = {293--303},
year = {2007}
}
@inproceedings{DBLP:journals/corr/FengLLZ16,
author = {Shi Feng and
Shujie Liu and
Mu Li and
Ming Zhou},
title = {Implicit Distortion and Fertility Models for Attention-based Encoder-Decoder
{NMT} Model},
publisher = {CoRR},
volume = {abs/1601.03317},
year = {2016}
}
@inproceedings{DBLP:conf/coling/UdupaFM04,
author = {Raghavendra Udupa and
Tanveer A. Faruquie and
Hemanta Kumar Maji},
title = {An Algorithmic Framework for Solving the Decoding Problem in Statistical
Machine Translation},
year = {2004},
publisher = {International Conference on Computational Linguistics}
}
@inproceedings{DBLP:conf/naacl/RiedelC09,
author = {Sebastian Riedel and
James Clarke},
title = {Revisiting Optimal Decoding for Machine Translation {IBM} Model 4},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009},
}
@inproceedings{DBLP:conf/eacl/UdupaM06,
author = {Raghavendra Udupa and
Hemanta Kumar Maji},
title = {Computational Complexity of Statistical Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{DBLP:conf/emnlp/LeuschMN08,
author = {Gregor Leusch and
Evgeny Matusov and
Hermann Ney},
title = {Complexity of Finding the BLEU-optimal Hypothesis in a Confusion Network},
pages = {839--847},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2008}
}
@inproceedings{DBLP:journals/mt/FlemingKN15,
author = {Noah Fleming and
Antonina Kolokolova and
Renesa Nizamee},
title = {Complexity of alignment and decoding problems: restrictions and approximations},
publisher = {Machine Translation},
volume = {29},
number = {3-4},
pages = {163--187},
year = {2015}
}
%%%%% chapter 5------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 6------------------------------------------------------
@inproceedings{ittycheriah2005maximum,
author = {Abraham Ittycheriah and
Salim Roukos},
title = {A Maximum Entropy Word Aligner for Arabic-English Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2005}
}
@inproceedings{koehn2003statistical,
author = {Philipp Koehn and
Franz Josef Och and
Daniel Marcu},
title = {Statistical Phrase-Based Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2003}
}
@book{manning1999foundations,
title ={Foundations of statistical natural language processing},
author ={Manning, Christopher D and Manning, Christopher D and Sch{\"u}tze, Hinrich},
year ={1999},
publisher ={Massachusetts Institute of Technology Press}
}
@inproceedings{och2003systematic,
author = {Franz Josef Och and
Hermann Ney},
title = {A Systematic Comparison of Various Statistical Alignment Models},
publisher = {Computational Linguistics},
volume = {29},
number = {1},
pages = {19--51},
year = {2003}
}
@inproceedings{och2004alignment,
author = {Franz Josef Och and
Hermann Ney},
title = {The Alignment Template Approach to Statistical Machine Translation},
publisher = {Computational Linguistics},
volume = {30},
number = {4},
pages = {417--449},
year = {2004}
}
@inproceedings{vogel1996hmm,
author = {Stephan Vogel and
Hermann Ney and
Christoph Tillmann},
title = {HMM-Based Word Alignment in Statistical Translation},
publisher = {International Conference on Computational Linguistics},
pages = {836--841},
year = {1996}
}
@inproceedings{xiao2013unsupervised,
title ={Unsupervised sub-tree alignment for tree-to-tree translation},
author ={Tong Xiao and Jingbo Zhu},
publisher ={Journal of Artificial Intelligence Research},
volume ={48},
pages ={733--782},
year ={2013}
}
@inproceedings{1966Decentering,
author = {Brown D.C.},
title = {Decentering Distortion of Lenses},
publisher = {Photogrammetric Engineering},
volume = {32},
pages = {444--462},
year = {1966}
}
@inproceedings{ClausF05,
author = {David Claus and
Andrew W. Fitzgibbon},
title = {A Rational Function Lens Distortion Model for General Cameras},
pages = {213--219},
publisher = {{IEEE} Computer Society Conference on Computer Vision and Pattern
Recognition},
year = {2005},
}
@inproceedings{ChiangLMMRS05,
author = {David Chiang and
Adam Lopez and
Nitin Madnani and
Christof Monz and
Philip Resnik and
Michael Subotin},
title = {The Hiero Machine Translation System: Extensions, Evaluation, and
Analysis},
pages = {779--786},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2005},
}
%%%%% chapter 6------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 7------------------------------------------------------
@inproceedings{DBLP:journals/tit/Viterbi67,
author = {Andrew J. Viterbi},
title = {Error bounds for convolutional codes and an asymptotically optimum
decoding algorithm},
publisher = {IEEE Transactions on Information Theory},
volume = {13},
number = {2},
pages = {260--269},
year = {1967}
}
@inproceedings{DBLP:conf/acl/OchN02,
author = {Franz Josef Och and
Hermann Ney},
title = {Discriminative Training and Maximum Entropy Models for Statistical
Machine Translation},
pages = {295--302},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2002}
}
@inproceedings{koehn2000estimating,
author = {Philipp Koehn and
Kevin Knight},
title = {Estimating Word Translation Probabilities from Unrelated Monolingual
Corpora Using the {EM} Algorithm},
pages = {711--715},
publisher = {AAAI Press},
year = {2000}
}
@inproceedings{taskar2005a,
author = {Benjamin Taskar and
Simon Lacoste-Julien and
Dan Klein},
title = {A Discriminative Matching Approach to Word Alignment},
pages = {73--80},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2005}
}
@inproceedings{DBLP:conf/coling/OchN00,
author = {Franz Josef Och and
Hermann Ney},
title = {A Comparison of Alignment Models for Statistical Machine Translation},
pages = {1086--1090},
publisher = {Morgan Kaufmann},
year = {2000}
}
@inproceedings{koehn2002learning,
author = {Kevin Knight},
title = {Learning a translation lexicon from monolingual corpora},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2002},
pages = {9--16}
}
@inproceedings{Gros2008MSD,
author ={Gros, Jerneja {\v{Z}}ganec},
title ={MSD Recombination Method in Statistical Machine Translation},
volume ={1060},
pages ={186--189},
publisher ={American Institute of Physics},
year ={2008},
}
@inproceedings{xiong2006maximum,
author = {Deyi Xiong and
Qun Liu and
Shouxun Lin},
title = {Maximum Entropy Based Phrase Reordering Model for Statistical Machine
Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{DBLP:conf/naacl/KumarB05,
author = {Shankar Kumar and
William J. Byrne},
title = {Local Phrase Reordering Models for Statistical Machine Translation},
pages = {161--168},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2005}
}
@inproceedings{li-etal-2014-neural,
author = {Peng Li and
Yang Liu and
Maosong Sun and
Tatsuya Izuha and
Dakun Zhang},
title = {A Neural Reordering Model for Phrase-based Translation},
pages = {1897--1907},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{powell1964an,
author = {M. J. D. Powell},
title = {An efficient method for finding the minimum of a function of several
variables without calculating derivatives},
publisher = {The Computer Journal},
volume = {7},
number = {2},
pages = {155--162},
year = {1964}
}
@inproceedings{DBLP:conf/emnlp/ChiangMR08,
author = {David Chiang and
Yuval Marton and
Philip Resnik},
title = {Online Large-Margin Training of Syntactic and Structural Translation
Features},
pages = {224--233},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2008}
}
@inproceedings{Hopkins2011Tuning,
author = {Mark Hopkins and
Jonathan May},
title = {Tuning as Ranking},
pages = {1352--1362},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2011}
}
@inproceedings{DBLP:conf/acl/KleinM03,
author = {Dan Klein and
Christopher D. Manning},
title = {Accurate Unlexicalized Parsing},
pages = {423--430},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2003}
}
@inproceedings{DBLP:conf/acl/OchW98,
author = {Franz Josef Och and
Hans Weber},
title = {Improving Statistical Natural Language Translation with Categories
and Rules},
pages = {985--989},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {1998}
}
@phdthesis{DBLP:phd/dnb/Och02,
author = {Franz Josef Och},
title = {Statistical machine translation: from single word models to alignment
templates},
publisher = {{RWTH} Aachen University, Germany},
year = {2002}
}
@inproceedings{DBLP:conf/acl/WangW98,
author = {Ye-Yi Wang and
Alex Waibel},
title = {Modeling with Structures in Statistical Machine Translation},
pages = {1357--1363},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {1998}
}
@inproceedings{DBLP:conf/acl/WatanabeSO03,
author = {Taro Watanabe and
Eiichiro Sumita and
Hiroshi G. Okuno},
title = {Chunk-Based Statistical Translation},
pages = {303--310},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2003}
}
@inproceedings{DBLP:conf/acl/Marcu01,
author = {Daniel Marcu},
title = {Towards a Unified Approach to Memory- and Statistical-Based Machine
Translation},
pages = {378--385},
publisher = {Morgan Kaufmann Publishers},
year = {2001}
}
@inproceedings{DBLP:conf/ki/ZensON02,
author = {Richard Zens and
Franz Josef Och and
Hermann Ney},
title = {Phrase-Based Statistical Machine Translation},
pages = {18--32},
publisher = {Annual Conference on Artificial Intelligence},
year = {2002}
}
@inproceedings{DBLP:conf/naacl/ZensN04,
author = {Richard Zens and
Hermann Ney},
title = {Improvements in Phrase-Based Statistical Machine Translation},
pages = {257--264},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2004}
}
@inproceedings{DBLP:conf/emnlp/MarcuW02,
author = {Daniel Marcu and
Daniel Wong},
title = {A Phrase-Based, Joint Probability Model for Statistical Machine Translation},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {133--139},
year = {2002}
}
@inproceedings{DBLP:conf/wmt/DeNeroGZK06,
author = {John DeNero and
Dan Gillick and
James Zhang and
Dan Klein},
title = {Why Generative Phrase Models Underperform Surface Heuristics},
pages = {31--38},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{german2011bilingual,
author = {German Sanchis-Trilles and
Daniel Ortiz-Martinez and
Jesus Gonzalez-Rubio and
Jorge Gonzalez and
Francisco Casacuberta},
title = {Bilingual segmentation for phrasetable pruning in Statistical Machine Translation},
pages = {257--264},
publisher = {Conference of the European Association for Machine Translation},
year = {2011}
}
@inproceedings{DBLP:conf/coling/BlackwoodGB08,
author = {Graeme W. Blackwood and
Adri{\`{a}} de Gispert and
William Byrne},
title = {Phrasal Segmentation Models for Statistical Machine Translation},
publisher = {International Conference on Computational Linguistics},
pages = {19--22},
year = {2008}
}
@inproceedings{DBLP:conf/naacl/XiongZL10,
author = {Deyi Xiong and
Min Zhang and
Haizhou Li},
title = {Learning Translation Boundaries for Phrase-Based Decoding},
pages = {136--144},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2010}
}
@inproceedings{DBLP:conf/naacl/Tillman04,
author = {Christoph Tillman},
title = {A Unigram Orientation Model for Statistical Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2004}
}
@inproceedings{DBLP:conf/acl/NagataSYO06,
author = {Masaaki Nagata and
Kuniko Saito and
Kazuhide Yamamoto and
Kazuteru Ohashi},
title = {A Clustered Global Phrase Reordering Model for Statistical Machine
Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{DBLP:conf/wmt/ZensN06,
author = {Richard Zens and
Hermann Ney},
title = {Discriminative Reordering Models for Statistical Machine Translation},
pages = {55--63},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{DBLP:conf/naacl/GreenGM10,
author = {Spence Green and
Michel Galley and
Christopher D. Manning},
title = {Improved Models of Distortion Cost for Statistical Machine Translation},
pages = {867--875},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2010}
}
@inproceedings{DBLP:conf/naacl/Cherry13,
author = {Colin Cherry},
title = {Improved Reordering for Phrase-Based Translation using Sparse Features},
pages = {22--31},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@inproceedings{DBLP:conf/wmt/HuckWRN13,
author = {Matthias Huck and
Joern Wuebker and
Felix Rietig and
Hermann Ney},
title = {A Phrase Orientation Model for Hierarchical Machine Translation},
pages = {452--463},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@inproceedings{matthias2012discriminative,
author = {Matthias Huck and
Stephan Peitz and
Markus Freitag and
Hermann Ney},
title = {Discriminative Reordering Extensions for Hierarchical Phrase-Based Machine Translation },
publisher = {International Conference on Material Engineering and Advanced Manufacturing Technology},
year = {2012}
}
@inproceedings{vinh2009improving,
author = {Vinh Van Nguyen and
Akira Shimazu and
Minh Le Nguyen and
Thai Phuong Nguyen},
title = {Improving a Lexicalized Hierarchical Reordering Model Using Maximum Entropy},
publisher = {Machine Translation Summit XII},
year = {2009}
}
@inproceedings{DBLP:journals/coling/BisazzaF16,
author = {Arianna Bisazza and
Marcello Federico},
title = {A Survey of Word Reordering in Statistical Machine Translation: Computational
Models and Language Phenomena},
publisher = {Computational Linguistics},
volume = {42},
number = {2},
pages = {163--205},
year = {2016}
}
@inproceedings{DBLP:conf/coling/XiaM04,
author = {Fei Xia and
Michael C. McCord},
title = {Improving a Statistical {MT} System with Automatically Learned Rewrite
Patterns},
publisher = {International Conference on Computational Linguistics},
year = {2004}
}
@inproceedings{DBLP:conf/acl/CollinsKK05,
author = {Michael Collins and
Philipp Koehn and
Ivona Kucerova},
title = {Clause Restructuring for Statistical Machine Translation},
pages = {531--540},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2005}
}
@inproceedings{DBLP:conf/emnlp/WangCK07,
author = {Chao Wang and
Michael Collins and
Philipp Koehn},
title = {Chinese Syntactic Reordering for Statistical Machine Translation},
pages = {737--745},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/ijcnlp/WuSDTN11,
author = {Xianchao Wu and
Katsuhito Sudoh and
Kevin Duh and
Hajime Tsukada and
Masaaki Nagata},
title = {Extracting Pre-ordering Rules from Predicate-Argument Structures},
pages = {29--37},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2011}
}
@inproceedings{DBLP:conf/coling/TillmannN00,
author = {Christoph Tillmann and
Hermann Ney},
title = {Word Re-ordering and DP-based Search in Statistical Machine Translation},
pages = {850--856},
publisher = {Morgan Kaufmann},
year = {2000}
}
@inproceedings{DBLP:conf/iwslt/ShenDA06a,
author = {Wade Shen and
Brian Delaney and
Timothy R. Anderson},
title = {An efficient graph search decoder for phrase-based statistical machine
translation},
pages = {197--204},
publisher = {International Symposium on Computer Architecture},
year = {2006}
}
@inproceedings{robert2007faster,
author = {Robert C. Moore and
Chris Quirk},
title = {Faster Beam-Search Decoding for Phrasal Statistical Machine Translation},
publisher = {Machine Translation Summit XI},
year = {2007}
}
@inproceedings{DBLP:conf/acl/HeafieldKM14,
author = {Kenneth Heafield and
Michael Kayser and
Christopher D. Manning},
title = {Faster Phrase-Based Decoding by Refining Feature State},
pages = {130--135},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/acl/WuebkerNZ12,
author = {Joern Wuebker and
Hermann Ney and
Richard Zens},
title = {Fast and Scalable Decoding with Language Model Look-Ahead for Phrase-based
Statistical Machine Translation},
pages = {28--32},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2012}
}
@inproceedings{DBLP:conf/iwslt/ZensN08,
author = {Richard Zens and
Hermann Ney},
title = {Improvements in dynamic programming beam search for phrase-based statistical
machine translation},
pages = {198--205},
publisher = {International Symposium on Computer Architecture},
year = {2008}
}
@inproceedings{och2004smorgasbord,
author = {Franz Josef Och and
Daniel Gildea and
Sanjeev Khudanpur and
Anoop Sarkar and
Kenji Yamada and
Alexander M. Fraser and
Shankar Kumar and
Libin Shen and
David Smith and
Katherine Eng and
Viren Jain and
Zhen Jin and
Dragomir R. Radev},
title = {A Smorgasbord of Features for Statistical Machine Translation},
pages = {161--168},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2004}
}
@inproceedings{Chiang200911,
author = {David Chiang and
Kevin Knight and
Wei Wang},
title = {11,001 New Features for Statistical Machine Translation},
pages = {218--226},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{gildea2003loosely,
author = {Daniel Gildea},
title = {Loosely Tree-Based Alignment for Machine Translation},
pages = {80--87},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2003}
}
@inproceedings{Blunsom2008A,
author = {Phil Blunsom and
Trevor Cohn and
Miles Osborne},
title = {A Discriminative Latent Variable Model for Statistical Machine Translation},
pages = {200--208},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2008}
}
@inproceedings{Blunsom2009A,
author = {Phil Blunsom and
Trevor Cohn and
Chris Dyer and
Miles Osborne},
title = {A Gibbs Sampler for Phrasal Synchronous Grammar Induction},
pages = {782--790},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{Cohn2009A,
author = {Trevor Cohn and
Phil Blunsom},
title = {A Bayesian Model of Syntax-Directed Tree to String Grammar Induction},
pages = {352--361},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{smith2006minimum,
author = {David A. Smith and
Jason Eisner},
title = {Minimum Risk Annealing for Training Log-Linear Models},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{li2009first,
author = {Zhifei Li and
Jason Eisner},
title = {First- and Second-Order Expectation Semirings with Applications to
Minimum-Risk Training on Translation Forests},
pages = {40--51},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{watanabe2007online,
author = {Taro Watanabe and
Jun Suzuki and
Hajime Tsukada and
Hideki Isozaki},
title = {Online Large-Margin Training for Statistical Machine Translation},
pages = {764--773},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007},
}
@inproceedings{dreyer2015apro,
author = {Markus Dreyer and
Yuanzhe Dong},
title = {{APRO:} All-Pairs Ranking Optimization for {MT} Tuning},
pages = {1018--1023},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{XiaoA,
author = {Tong Xiao and
Derek F. Wong and
Jingbo Zhu},
title = {A Loss-Augmented Approach to Training Syntactic Machine Translation
Systems},
publisher = {IEEE Transactions on Audio, Speech, and Language Processing},
volume = {24},
number = {11},
pages = {2069--2083},
year = {2016}
}
@book{marcu2006practical,
title={Practical structured learning techniques for natural language processing},
author={Daume Iii, Harold Charles },
publisher={University of Southern California},
year={2006},
}
@inproceedings{DBLP:conf/emnlp/SchwenkCF07,
author = {Holger Schwenk and
Marta R. Costa-juss{\`{a}} and
Jos{\'{e}} A. R. Fonollosa},
title = {Smooth Bilingual N-Gram Translation},
pages = {430--438},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{boxing2011unpacking,
author = {Boxing Chen and
Roland Kuhn and
George Foster and
Howard Johnson},
title = {Unpacking and Transforming Feature Functions: New Ways to Smooth Phrase Tables},
publisher = {Machine Translation Summit},
year = {2011}
}
@inproceedings{DBLP:conf/coling/DuanSZ10,
author = {Nan Duan and
Hong Sun and
Ming Zhou},
title = {Translation Model Generalization using Probability Averaging for Machine
Translation},
publisher = {International Conference on Computational Linguistics},
year = {2010}
}
@inproceedings{DBLP:conf/naacl/QuirkM06,
author = {Christopher Quirk and
Arul Menezes},
title = {Do we need phrases? Challenging the conventional wisdom in Statistical
Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{DBLP:journals/coling/MarinoBCGLFC06,
author = {Jos{\'{e}} B. Mari{\~{n}}o and
Rafael E. Banchs and
Josep Maria Crego and
Adri{\`{a}} de Gispert and
Patrik Lambert and
Jos{\'{e}} A. R. Fonollosa and
Marta R. Costa-juss{\`{a}}},
title = {\emph{N}-gram-based Machine Translation},
publisher = {Computational Linguistics},
volume = {32},
number = {4},
pages = {527--549},
year = {2006}
}
@inproceedings{DBLP:conf/emnlp/ZensSX12,
author = {Richard Zens and
Daisy Stanton and
Peng Xu},
title = {A Systematic Comparison of Phrase Table Pruning Techniques},
pages = {972--983},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2012}
}
@inproceedings{DBLP:conf/emnlp/JohnsonMFK07,
author = {Howard Johnson and
Joel D. Martin and
George F. Foster and
Roland Kuhn},
title = {Improving Translation Quality by Discarding Most of the Phrasetable},
pages = {967--975},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/emnlp/LingGTB12,
author = {Wang Ling and
Jo{\~{a}}o Gra{\c{c}}a and
Isabel Trancoso and
Alan W. Black},
title = {Entropy-based Pruning for Phrase-based Machine Translation},
pages = {962--971},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2012}
}
@inproceedings{DBLP:conf/naacl/ZettlemoyerM07,
author = {Luke S. Zettlemoyer and
Robert C. Moore},
title = {Selective Phrase Pair Extraction for Improved Statistical Machine
Translation},
pages = {209--212},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/naacl/EckVW07,
author = {Matthias Eck and
Stephan Vogel and
Alex Waibel},
title = {Translation Model Pruning via Usage Statistics for Statistical Machine
Translation},
pages = {21--24},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007},
}
@inproceedings{DBLP:conf/acl/Callison-BurchBS05,
author = {Chris Callison-Burch and
Colin J. Bannard and
Josh Schroeder},
title = {Scaling Phrase-Based Statistical Machine Translation to Larger Corpora
and Longer Phrases},
pages = {255--262},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2005}
}
@inproceedings{DBLP:conf/acl/Callison-BurchBS05,
author = {Paul McNamee and James Mayfield},
title = {Translation of Multiword Expressions Using Parallel Suffix Arrays},
publisher = {Association for Machine Translation in the Americas},
year = {2006}
}
@inproceedings{DBLP:conf/naacl/ZensN07,
author = {Richard Zens and
Hermann Ney},
title = {Efficient Phrase-Table Representation for Machine Translation with
Applications to Online {MT} and Speech Translation},
pages = {492--499},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{2014Dynamic,
title={Dynamic Phrase Tables for Machine Translation in an Interactive Post-editing Scenario},
author={Ulrich Germann },
publisher = {Association for Machine Translation in the Americas},
year={2014},
}
%%%%% chapter 7------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 8------------------------------------------------------
@inproceedings{Chiang2012Hope,
author = {David Chiang},
title = {Hope and Fear for Discriminative Training of Statistical Translation
Models},
publisher = {Journal of Machine Learning Research},
volume = {13},
pages = {1159--1187},
year = {2012}
}
@inproceedings{chiang2007hierarchical,
title={Hierarchical Phrase-Based Translation},
author ={David Chiang},
publisher ={Computational Linguistics},
volume ={33},
number ={2},
pages ={201--228},
year ={2007}
}
@book{cocke1969programming,
title ={Programming Languages and Their Compilers: Preliminary Notes},
author ={Cocke, John and Schwartz, J.T.},
year ={1970},
publisher ={Courant Institute of Mathematical Sciences, New York University}
}
@inproceedings{younger1967recognition,
author = {Daniel H. Younger},
title = {Recognition and Parsing of Context-Free Languages in Time n{\^{3}}},
publisher = {Information and Control},
volume = {10},
number = {2},
pages = {189--208},
year = {1967}
}
@inproceedings{kasami1966efficient,
author ={Tadao Kasami},
title ={An efficient recognition and syntax-analysis algorithm for context-free languages},
publisher ={Coordinated Science Laboratory Report no. R-257},
year ={1966}
}
@inproceedings{huang2005better,
author = {Liang Huang and
David Chiang},
title = {Better k-best Parsing},
pages = {53--64},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2005}
}
@inproceedings{wu1997stochastic,
author = {Dekai Wu},
title = {Stochastic Inversion Transduction Grammars and Bilingual Parsing of
Parallel Corpora},
publisher = {Computational Linguistics},
volume = {23},
number = {3},
pages = {377--403},
year = {1997}
}
@inproceedings{huang2006statistical,
title ={Statistical syntax-directed translation with extended domain of locality},
author ={Liang Huang and Kevin Knight and Aravind Joshi},
pages ={66--73},
year ={2006},
publisher ={Computationally Hard Problems \& Joint Inference in Speech \& Language Processing}
}
@inproceedings{galley2004s,
title ={What’s in a translation rule?},
author ={Michel Galleyand Mark Hopkins and Kevin Knight and Daniel Marcu},
publisher={Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics},
pages ={273--280},
year ={2004}
}
@inproceedings{eisner2003learning,
author = {Jason Eisner},
title = {Learning Non-Isomorphic Tree Mappings for Machine Translation},
pages = {205--208},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2003}
}
@inproceedings{zhang2008tree,
author = {Min Zhang and
Hongfei Jiang and
AiTi Aw and
Haizhou Li and
Chew Lim Tan and
Sheng Li},
title = {A Tree Sequence Alignment-based Tree-to-Tree Translation Model},
pages = {559--567},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2008}
}
@inproceedings{liu2009improving,
author = {Yang Liu and
Yajuan L{\"{u}} and
Qun Liu},
title = {Improving Tree-to-Tree Translation with Packed Forests},
pages = {558--566},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009},
}
@inproceedings{chiang2010learning,
author = {David Chiang},
title = {Learning to Translate with Source and Target Syntax},
pages = {1443--1452},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2010}
}
@inproceedings{marcu2006spmt,
author = {Daniel Marcu and
Wei Wang and
Abdessamad Echihabi and
Kevin Knight},
title = {{SPMT:} Statistical Machine Translation with Syntactified Target Language
Phrases},
pages = {44--52},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{xue2005building,
title={Building a large annotated Chinese corpus: the Penn Chinese treebank},
author={Xue, Nianwen and Xia, Fei and dong Chiou, Fu and Palmer, Martha},
publisher ={Journal of Natural Language Engineering},
volume={11},
number={2},
pages={207--238},
year={2005}
}
@inproceedings{DBLP:journals/coling/MarcusSM94,
author = {Mitchell P. Marcus and
Beatrice Santorini and
Mary Ann Marcinkiewicz},
title = {Building a Large Annotated Corpus of English: The Penn Treebank},
publisher = {Computational Linguistics},
volume = {19},
number = {2},
pages = {313--330},
year = {1993}
}
@inproceedings{DBLP:conf/naacl/ZhangHGK06,
author = {Hao Zhang and
Liang Huang and
Daniel Gildea and
Kevin Knight},
title = {Synchronous Binarization for Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{Tong2009Better,
author = {Tong Xiao and
Mu Li and
Dongdong Zhang and
Jingbo Zhu and
Ming Zhou},
title = {Better Synchronous Binarization for Machine Translation},
pages = {362--370},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{charniak2006multilevel,
title={Multilevel Coarse-to-Fine PCFG Parsing},
author={Eugene {Charniak} and Mark {Johnson} and Micha {Elsner} and Joseph {Austerweil} and David {Ellis} and Isaac {Haxton} and Catherine {Hill} and R. {Shrivaths} and Jeremy {Moore} and Michael {Pozar} and Theresa {Vu}},
publisher={Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics},
pages={168--175},
year={2006}
}
@inproceedings{DBLP:conf/coling/GrovesHW04,
author = {Declan Groves and
Mary Hearne and
Andy Way},
title = {Robust Sub-Sentential Alignment of Phrase-Structure Trees},
publisher = {International Conference on Computational Linguistics},
year = {2004}
}
@inproceedings{DBLP:conf/coling/SunZT10,
author = {Jun Sun and
Min Zhang and
Chew Lim Tan},
title = {Discriminative Induction of Sub-Tree Alignment using Limited Labeled
Data},
pages = {1047--1055},
publisher = {International Conference on Computational Linguistics},
year = {2010}
}
@inproceedings{liu2009weighted,
author = {Yang Liu and
Tian Xia and
Xinyan Xiao and
Qun Liu},
title = {Weighted Alignment Matrices for Statistical Machine Translation},
pages = {1017--1026},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{sun2010exploring,
author = {Jun Sun and
Min Zhang and
Chew Lim Tan},
title = {Exploring Syntactic Structural Features for Sub-Tree Alignment Using
Bilingual Tree Kernels},
pages = {306--315},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2010}
}
@inproceedings{ilprints729,
title={Parsing and Hypergraphs},
author={Klein, Dan and Manning, Christopher D.},
publisher ={New Developments in Parsing Technology},
volume={65},
number={3},
pages={123--134},
year={2001},
}
@inproceedings{goodman1999semiring,
author = {Joshua Goodman},
title = {Semiring Parsing},
publisher = {Computational Linguistics},
volume = {25},
number = {4},
pages = {573--605},
year = {1999}
}
@inproceedings{eisner2002parameter,
author = {Jason Eisner},
title = {Parameter Estimation for Probabilistic Finite-State Transducers},
pages = {1--8},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2002}
}
@inproceedings{zhu2011improving,
author = {Jingbo Zhu and
Tong Xiao},
title = {Improving Decoding Generalization for Tree-to-String Translation},
pages = {418--423},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2011}
}
@inproceedings{DBLP:conf/acl/AlshawiBX97,
author = {Hiyan Alshawi and
Adam L. Buchsbaum and
Fei Xia},
title = {A Comparison of Head Transducers and Transfer for a Limited Domain
Translation Application},
pages = {360--365},
publisher = {Morgan Kaufmann Publishers},
year = {1997}
}
@inproceedings{DBLP:conf/acl-vlc/Wu95,
author = {Dekai Wu},
title = {Trainable Coarse Bilingual Grammars for Parallel Text Bracketing},
publisher = {Third Workshop on Very Large Corpor},
year = {1995}
}
@inproceedings{DBLP:conf/acl/WuW98,
author = {Dekai Wu and
Hongsing Wong},
title = {Machine Translation with a Stochastic Grammatical Channel},
pages = {1408--1415},
publisher = {Morgan Kaufmann Publishers},
year = {1998}
}
@inproceedings{ja2006obtaining,
author = {J.A.Sánchez and J.M.Benedí.},
title = {Obtaining Word Phrases with Stochastic Inversion Transduction Grammars for Phrase-based Statistical Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{DBLP:conf/acl/ZhangQMG08,
author = {Hao Zhang and
Chris Quirk and
Robert C. Moore and
Daniel Gildea},
title = {Bayesian Learning of Non-Compositional Phrases with Synchronous Parsing},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2008}
}
@inproceedings{DBLP:conf/coling/ZollmannVOP08,
author = {Andreas Zollmann and
Ashish Venugopal and
Franz Josef Och and
Jay M. Ponte},
title = {A Systematic Comparison of Phrase-Based, Hierarchical and Syntax-Augmented
Statistical {MT}},
publisher = {International Conference on Computational Linguistics},
pages = {1145--1152},
year = {2008}
}
@inproceedings{DBLP:conf/acl/WatanabeTI06,
author = {Taro Watanabe and
Hajime Tsukada and
Hideki Isozaki},
title = {Left-to-Right Target Generation for Hierarchical Phrase-Based Translation},
publisher = {Annual Meeting of the Association for Computational Linguisticss},
year = {2006}
}
@inproceedings{DBLP:conf/naacl/GalleyHKM04,
author = {Michel Galley and
Mark Hopkins and
Kevin Knight and
Daniel Marcu},
title = {What's in a translation rule?},
pages = {273--280},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2004}
}
@inproceedings{DBLP:conf/naacl/HuangK06,
author = {Bryant Huang and
Kevin Knight},
title = {Relabeling Syntax Trees to Improve Syntax-Based Machine Translation
Quality},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{DBLP:conf/emnlp/DeNeefeKWM07,
author = {Steve DeNeefe and
Kevin Knight and
Wei Wang and
Daniel Marcu},
title = {What Can Syntax-Based {MT} Learn from Phrase-Based MT?},
pages = {755--763},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/wmt/LiuG08,
author = {Ding Liu and
Daniel Gildea},
title = {Improved Tree-to-String Transducer for Machine Translation},
pages = {62--69},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2008}
}
@INPROCEEDINGS{Nesson06inductionof,
author = {Rebecca Nesson and Stuart M. Shieber and Alexander Rush},
title = {Induction of probabilistic synchronous tree-insertion grammars for machine translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@MISC{Zhang07atree-to-tree,
author = {Min Zhang and Hongfei Jiang and Ai Ti Aw and Jun Sun and Sheng Li and Chew Lim Tan},
title = {A Tree-to-Tree Alignment-based Model for Statistical Machine Translation},
year = {2007},
publisher = {Machine Translation Summit}
}
@inproceedings{DBLP:conf/emnlp/WangKM07,
author = {Wei Wang and
Kevin Knight and
Daniel Marcu},
title = {Binarizing Syntax Trees to Improve Syntax-Based Machine Translation
Accuracy},
pages = {746--754},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/acl/MiHL08,
author = {Haitao Mi and
Liang Huang and
Qun Liu},
title = {Forest-Based Translation},
pages = {192--199},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2008}
}
@inproceedings{DBLP:conf/emnlp/MiH08,
author = {Haitao Mi and
Liang Huang},
title = {Forest-based Translation Rule Extraction},
pages = {206--214},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2008}
}
@inproceedings{DBLP:conf/emnlp/ZhangZZ11,
author = {Jiajun Zhang and
Feifei Zhai and
Chengqing Zong},
title = {Augmenting String-to-Tree Translation Models with Fuzzy Use of Source-side
Syntax},
pages = {204--215},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2011}
}
@inproceedings{DBLP:conf/wmt/ZollmannV06,
author = {Andreas Zollmann and
Ashish Venugopal},
title = {Syntax Augmented Machine Translation via Chart Parsing},
pages = {138--141},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{DBLP:conf/acl/MartonR08,
author = {Yuval Marton and
Philip Resnik},
title = {Soft Syntactic Constraints for Hierarchical Phrased-Based Translation},
pages = {1003--1011},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2008}
}
@inproceedings{DBLP:conf/wmt/PopelMGZ11,
author = {Martin Popel and
David Marecek and
Nathan Green and
Zdenek Zabokrtsk{\'{y}}},
title = {Influence of Parser Choice on Dependency-Based {MT}},
pages = {433--439},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2011}
}
@inproceedings{DBLP:conf/coling/XiaoZZZ10,
author = {Tong Xiao and
Jingbo Zhu and
Hao Zhang and
Muhua Zhu},
title = {An Empirical Study of Translation Rule Extraction with Multiple Parsers},
pages = {1345--1353},
publisher = {Chinese Information Processing Society of China},
year = {2010}
}
@inproceedings{Zhai2012Treebased,
title={Treebased translation without using parse trees},
author = {Feifei Zhai and
Jiajun Zhang and
Yu Zhou and
Chengqing Zong},
publisher = {International Conference on Computational Linguistics},
year={2012},
}
@inproceedings{DBLP:journals/tacl/ZhaiZZZ13,
author = {Feifei Zhai and
Jiajun Zhang and
Yu Zhou and
Chengqing Zong},
title = {Unsupervised Tree Induction for Tree-based Translation},
publisher = {Transactions of Association for Computational Linguistic},
volume = {1},
pages = {243--254},
year = {2013}
}
@inproceedings{DBLP:journals/mt/QuirkM06,
author = {Christopher Quirk and
Arul Menezes},
title = {Dependency treelet translation: the convergence of statistical and
example-based machine-translation?},
publisher = {Machine Translation},
volume = {20},
number = {1},
pages = {43--65},
year = {2006}
}
@inproceedings{DBLP:conf/wmt/XiongLL07,
author = {Deyi Xiong and
Qun Liu and
Shouxun Lin},
title = {A Dependency Treelet String Correspondence Model for Statistical Machine
Translation},
pages = {40--47},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/coling/Lin04,
author = {Dekang Lin},
title = {A Path-based Transfer Model for Machine Translation},
publisher = {International Conference on Computational Linguistics},
year = {2004}
}
@inproceedings{DBLP:conf/acl/DingP05,
author = {Yuan Ding and
Martha Palmer},
title = {Machine Translation Using Probabilistic Synchronous Dependency Insertion
Grammars},
pages = {541--548},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2005}
}
@inproceedings{DBLP:conf/coling/ChenXMJL14,
author = {Hongshen Chen and
Jun Xie and
Fandong Meng and
Wenbin Jiang and
Qun Liu},
title = {A Dependency Edge-based Transfer Model for Statistical Machine Translation},
pages = {1103--1113},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/coling/SuLMZLL10,
author = {Jinsong Su and
Yang Liu and
Haitao Mi and
Hongmei Zhao and
Yajuan Lv and
Qun Liu},
title = {Dependency-Based Bracketing Transduction Grammar for Statistical Machine
Translation},
pages = {1185--1193},
publisher = {Chinese Information Processing Society of China},
year = {2010}
}
@inproceedings{DBLP:conf/coling/XieXL14,
author = {Jun Xie and
Jinan Xu and
Qun Liu},
title = {Augment Dependency-to-String Translation with Fixed and Floating Structures},
pages = {2217--2226},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/emnlp/LiWL15,
author = {Liangyou Li and
Andy Way and
Qun Liu},
title = {Dependency Graph-to-String Translation},
pages = {33--43},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:conf/acl/MiL10,
author = {Haitao Mi and
Qun Liu},
title = {Constituency to Dependency Translation with Forests},
pages = {1433--1442},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2010}
}
@inproceedings{DBLP:conf/coling/TuLHLL10,
author = {Zhaopeng Tu and
Yang Liu and
Young-Sook Hwang and
Qun Liu and
Shouxun Lin},
title = {Dependency Forest for Statistical Machine Translation},
pages = {1092--1100},
publisher = {International Conference on Computational Linguistics},
year = {2010}
}
@inproceedings{bangalore2001computing,
title ={Computing consensus translation from multiple machine translation systems},
author ={Srinivas Bangalore, German Bordel and Giuseppe Riccardi},
publisher = {IEEE Workshop on Automatic Speech Recognition and Understanding},
pages ={351--354},
year ={2001}
}
@inproceedings{rosti2007combining,
author = {Antti-Veikko I. Rosti and
Necip Fazil Ayan and
Bing Xiang and
Spyridon Matsoukas and
Richard M. Schwartz and
Bonnie J. Dorr},
title = {Combining Outputs from Multiple Machine Translation Systems},
pages = {228--235},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{xiao2013bagging,
title ={Bagging and boosting statistical machine translation systems},
author ={Tong Xiao and Jingbo Zhu and Tongran Liu },
publisher ={Artificial Intelligence},
volume ={195},
pages ={496--527},
year ={2013}
}
@inproceedings{Yang2009Lattice,
author = {Yang Feng and
Yang Liu and
Haitao Mi and
Qun Liu and
Yajuan L{\"{u}}},
title = {Lattice-based System Combination for Statistical Machine Translation},
pages = {1105--1113},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{He2008Indirect,
author = {Xiaodong He and
Mei Yang and
Jianfeng Gao and
Patrick Nguyen and
Robert C. Moore},
title = {Indirect-HMM-based Hypothesis Alignment for Combining Outputs from
Machine Translation Systems},
pages = {98--107},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2008}
}
@inproceedings{Li2009Incremental,
author = {Chi-Ho Li and
Xiaodong He and
Yupeng Liu and
Ning Xi},
title = {Incremental {HMM} Alignment for {MT} System Combination},
pages = {949--957},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{Yang2009Joint,
author = {Yang Liu and
Haitao Mi and
Yang Feng and
Qun Liu},
title = {Joint Decoding with Multiple Translation Models},
pages = {576--584},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{Mu2009Collaborative,
author = {Mu Li and
Nan Duan and
Dongdong Zhang and
Chi-Ho Li and
Ming Zhou},
title = {Collaborative Decoding: Partial Hypothesis Re-ranking Using Translation
Consensus between Decoders},
pages = {585--592},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{Tong2016Syntactic,
author = {Tong Xiao and
Jingbo Zhu and
Chunliang Zhang and
Tongran Liu},
title = {Syntactic Skeleton-Based Translation},
pages = {2856--2862},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2016},
}
@inproceedings{charniak2001immediate,
author = {Eugene Charniak},
title = {Immediate-Head Parsing for Language Models},
pages = {116--123},
publisher = {Morgan Kaufmann Publishers},
year = {2001}
}
@inproceedings{shen2008a,
author = {Libin Shen and
Jinxi Xu and
Ralph M. Weischedel},
title = {A New String-to-Dependency Machine Translation Algorithm with a Target
Dependency Language Model},
pages = {577--585},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2008}
}
@inproceedings{xiao2011language,
title ={Language Modeling for Syntax-Based Machine Translation Using Tree Substitution Grammars: A Case Study on Chinese-English Translation},
author ={Xiao, Tong and Zhu, Jingbo and Zhu, Muhua},
volume ={10},
number ={4},
pages ={1--29},
year ={2011},
publisher ={ACM Transactions on Asian Language Information Processing (TALIP)}
}
%%%%% chapter 8------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 9------------------------------------------------------
@inproceedings{brown1992class,
title={Class-based n-gram models of natural language},
author={Peter F. Brown and
Vincent J. Della Pietra and
Peter V. De Souza and
Jennifer C. Lai and
Robert L. Mercer},
publisher={Computational linguistics},
volume={18},
number={4},
pages={467--479},
year={1992}
}
@inproceedings{mikolov2012context,
title={Context dependent recurrent neural network language model},
author={Tomas Mikolov and
Geoffrey Zweig},
publisher={IEEE Spoken Language Technology Workshop},
pages={234--239},
year={2012}
}
@inproceedings{zaremba2014recurrent,
title={Recurrent Neural Network Regularization},
author={Wojciech Zaremba and
Ilya Sutskever and
Oriol Vinyals},
publisher={arXiv: Neural and Evolutionary Computing},
year={2014}
}
@inproceedings{zilly2016recurrent,
title={Recurrent Highway Networks},
author={Julian G. Zilly and
Rupesh Kumar Srivastava and
Jan Koutn{\'{\i}}k and
J{\"{u}}rgen Schmidhuber},
publisher={International Conference on Machine Learning},
year={2016}
}
@inproceedings{merity2017regularizing,
title={Regularizing and optimizing LSTM language models},
author={Stephen Merity and
Nitish Shirish Keskar and
Richard Socher},
publisher={International Conference on Learning Representations},
year={2017}
}
@inproceedings{radford2019language,
title ={Language models are unsupervised multitask learners},
author ={Radford, Alec and Wu, Jeffrey and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya},
publisher ={OpenAI Blog},
volume ={1},
number ={8},
pages ={9},
year ={2019}
}
@inproceedings{baydin2017automatic,
title ={Automatic differentiation in machine learning: a survey},
author ={Baydin, At{\i}l{\i}m G{\"u}nes and Pearlmutter, Barak A and Radul, Alexey Andreyevich and Siskind, Jeffrey Mark},
publisher ={Journal of Machine Learning Research},
volume ={18},
number ={1},
pages ={5595--5637},
year ={2017}
}
@inproceedings{qian1999momentum,
author = {Ning Qian},
title = {On the momentum term in gradient descent learning algorithms},
publisher = {Neural Networks},
volume = {12},
number = {1},
pages = {145--151},
year = {1999},
}
@inproceedings{duchi2011adaptive,
author = {John C. Duchi and
Elad Hazan and
Yoram Singer},
title = {Adaptive Subgradient Methods for Online Learning and Stochastic Optimization},
publisher = {Journal of Machine Learning Research},
volume = {12},
pages = {2121--2159},
year = {2011},
}
@inproceedings{tieleman2012rmsprop,
title ={Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude},
author ={Tieleman, Tijmen and Hinton, Geoffrey},
publisher ={COURSERA: Neural networks for machine learning},
volume ={4},
number ={2},
pages ={26--31},
year ={2012}
}
@inproceedings{kingma2014adam,
author = {Diederik P. Kingma and
Jimmy Ba},
title = {Adam: {A} Method for Stochastic Optimization},
publisher = {International Conference on Learning Representations},
year = {2015}
}
@inproceedings{ioffe2015batch,
author = {Sergey Ioffe and
Christian Szegedy},
title = {Batch Normalization: Accelerating Deep Network Training by Reducing
Internal Covariate Shift},
publisher = {International Conference on Machine Learning},
volume = {37},
pages = {448--456},
year = {2015}
}
@inproceedings{Ba2016LayerN,
author = {Lei Jimmy Ba and
Jamie Ryan Kiros and
Geoffrey Hinton},
title = {Layer Normalization},
publisher = {CoRR},
volume = {abs/1607.06450},
year = {2016}
}
@inproceedings{mikolov2013distributed,
author = {Tomas Mikolov and
Ilya Sutskever and
Kai Chen and
Gregory S. Corrado and
Jeffrey Dean},
title = {Distributed Representations of Words and Phrases and their Compositionality},
publisher = {Conference on Neural Information Processing Systems},
pages = {3111--3119},
year = {2013}
}
@inproceedings{arthur2016incorporating,
author = {Philip Arthur and
Graham Neubig and
Satoshi Nakamura},
title = {Incorporating Discrete Translation Lexicons into Neural Machine Translation},
pages = {1557--1567},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2016}
}
@inproceedings{stahlberg2016syntactically,
author = {Felix Stahlberg and
Eva Hasler and
Aurelien Waite and
Bill Byrne},
title = {Syntactically Guided Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016},
}
@inproceedings{plank2013embedding,
author = {Barbara Plank and
Alessandro Moschitti},
title = {Embedding Semantic Similarity in Tree Kernels for Domain Adaptation
of Relation Extraction},
pages = {1498--1507},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@inproceedings{perozzi2014deepwalk,
author = {Bryan Perozzi and
Rami Al-Rfou and
Steven Skiena},
title = {DeepWalk: online learning of social representations},
publisher = {ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
pages = {701--710},
year = {2014}
}
@inproceedings{2011Natural,
title={Natural Language Processing (almost) from Scratch},
author={ Collobert, Ronan and Weston, Jason and Bottou, Léon and Karlen, Michael and Kavukcuoglu, Koray and Kuksa, Pavel },
publisher={Journal of Machine Learning Research},
volume={12},
number={1},
pages={2493-2537},
year={2011}
}
@inproceedings{mccann2017learned,
author = {Bryan Mccann and
James Bradbury and
Caiming Xiong and
Richard Socher},
title = {Learned in Translation: Contextualized Word Vectors},
publisher = {Conference on Neural Information Processing Systems},
pages = {6294--6305},
year = {2017}
}
%%%%%%%%%%%%%%%%%%%%%%%神经语言模型，已检查修改%%%%%%%%%%%%%%%%%%%%%%%%%
@inproceedings{Peters2018DeepCW,
title={Deep contextualized word representations},
author={Matthew Peters and
Mark Neumann and
Mohit Iyyer and
Matt Gardner and
Christopher Clark and
Kenton Lee and
Luke Zettlemoyer},
publisher={Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics},
year={2018}
}
@inproceedings{Graves2013HybridSR,
title={Hybrid speech recognition with Deep Bidirectional LSTM},
author={Alex Graves and
Navdeep Jaitly and
Abdel-rahman Mohamed},
publisher={IEEE Workshop on Automatic Speech Recognition and Understanding},
year={2013},
pages={273-278}
}
@inproceedings{Verwimp2017CharacterWordLL,
title={Character-Word LSTM Language Models},
author={Lyan Verwimp and
Joris Pelemans and
Hugo Van Hamme and
Patrick Wambacq},
publisher={Annual Conference of the European Association for Machine Translation},
year={2017}
}
@inproceedings{Onoe2016GatedWR,
author = {Yasumasa Miyamoto and
Kyunghyun Cho},
title = {Gated Word-Character Recurrent Language Model},
pages = {1992--1997},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2016}
}
@inproceedings{Hwang2017CharacterlevelLM,
title={Character-level language modeling with hierarchical recurrent neural networks},
author={Kyuyeon Hwang and
Wonyong Sung},
publisher={International Conference on Acoustics, Speech and Signal Processing},
year={2017},
pages={5720-5724}
}
@inproceedings{Kim2016CharacterAwareNL,
title={Character-Aware Neural Language Models},
author={Yoon Kim and
Yacine Jernite and
David Sontag and
Alexander M. Rush},
publisher={AAAI Conference on Artificial Intelligence},
year={2016}
}
@inproceedings{Ahn2016ANK,
title={A Neural Knowledge Language Model},
author={Sungjin Ahn and
Heeyoul Choi and
Tanel P{\"a}rnamaa and
Yoshua Bengio},
publisher={arXiv preprint arXiv:1608.00318},
year={2016}
}
@inproceedings{Wang2015LargerContextLM,
title={Larger-Context Language Modelling},
author={Tian Wang and
Kyunghyun Cho},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2015}
}
@inproceedings{Adel2015SyntacticAS,
title={Syntactic and Semantic Features For Code-Switching Factored Language Models},
author={Heike Adel and
Ngoc Vu and
Katrin Kirchhoff and
Dominic Telaar and
Tanja Schultz},
publisher={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
year={2015},
volume={23},
pages={431-440}
}
@inproceedings{Wu2012FactoredLM,
title={Factored Language Model based on Recurrent Neural Network},
author={Youzheng Wu and
Xugang Lu and
Hitoshi Yamamoto and
Shigeki Matsuda and
Chiori Hori and
Hideki Kashioka},
publisher={International Conference on Computational Linguistics},
year={2012}
}
@inproceedings{Pham2016ConvolutionalNN,
title={Convolutional Neural Network Language Models},
author={Ngoc-quan Pham and
German Kruszewski and
Gemma Boleda},
publisher={Conference on Empirical Methods in Natural Language Processing},
year={2016}
}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%深度阅读修改和补充，待检查修改%%%%%%%%%%%%%%%%%%%
@inproceedings{moraffah2020causal,
title={Causal Interpretability for Machine Learning-Problems, Methods and Evaluation},
author={Raha Moraffah and
Mansooreh Karami and
Ruocheng Guo and
Adrienne Raglin and
Huan Liu},
publisher={ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
volume={22},
number={1},
pages={18--33},
year={2020}
}
@incollection{nguyen2019understanding,
title={Understanding neural networks via feature visualization: A survey},
author={Anh Nguyen and
Jason Yosinski and
Jeff Clune},
pages={55--76},
year={2019},
publisher={Springer}
}
@inproceedings{yang2017improving,
title={Improving adversarial neural machine translation with prior knowledge},
author={Yating Yang and
Xiao Li and
Tonghai Jiang and
Jinying Kong and
Bo Ma and
Xi Zhou and
Lei Wang },
publisher={IEEE Global Conference on Signal and Information Processing},
pages={1373--1377},
year={2017}
}
@inproceedings{currey2019incorporating,
title={Incorporating source syntax into transformer-based neural machine translation},
author={Anna Currey and
Kenneth Heafield},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={24--33},
year={2019}
}
@inproceedings{currey2018multi,
title={Multi-source syntactic neural machine translation},
author={Anna Currey and
Kenneth Heafield},
publisher={Conference on Empirical Methods in Natural Language Processing},
year={2018}
}
@inproceedings{marevcek2018extracting,
title={Extracting syntactic trees from transformer encoder self-attentions},
author={David Mare{\v{c}}ek
and Rudolf Rosa},
publisher={Conference on Empirical Methods in Natural Language Processing},
pages={347--349},
year={2018}
}
@inproceedings{blevins2018deep,
title={Deep rnns encode soft hierarchical syntax},
author={Blevins, Terra and Levy, Omer and Zettlemoyer, Luke},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2018}
}
@inproceedings{Yin2018StructVAETL,
title={StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing},
author={Pengcheng Yin and
Chunting Zhou and
Junxian He and
Graham Neubig},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2018}
}
@inproceedings{Aharoni2017TowardsSN,
title={Towards String-To-Tree Neural Machine Translation},
author={Roee Aharoni and
Yoav Goldberg},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2017}
}
@inproceedings{Bastings2017GraphCE,
title={Graph Convolutional Encoders for Syntax-aware Neural Machine Translation},
author={Jasmijn Bastings and
Ivan Titov and Wilker Aziz and
Diego Marcheggiani and
Khalil Sima'an},
publisher={Conference on Empirical Methods in Natural Language Processing},
year={2017}
}
@inproceedings{KoncelKedziorski2019TextGF,
title={Text Generation from Knowledge Graphs with Graph Transformers},
author={Rik Koncel-Kedziorski and
Dhanush Bekal and Yi Luan and
Mirella Lapata and
Hannaneh Hajishirzi},
publisher={Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year={2019}
}
@inproceedings{Kovalerchuk2020SurveyOE,
title={Survey of explainable machine learning with visual and granular methods beyond quasi-explanations},
author={Boris Kovalerchuk and
Muhammad Ahmad and
Ankur Teredesai},
publisher={ArXiv},
year={2020},
volume={abs/2009.10221}
}
@inproceedings{DoshiVelez2017TowardsAR,
title={Towards A Rigorous Science of Interpretable Machine Learning},
author={Finale Doshi-Velez and
Been Kim},
publisher={arXiv preprint arXiv:1702.08608},
year={2017}
}
@inproceedings{Dozat2016IncorporatingNM,
title={Incorporating Nesterov Momentum into Adam},
author={Timothy Dozat},
publisher={International Conference on Learning Representations},
year={2016}
}
@inproceedings{Reddi2018OnTC,
author = {Sashank J. Reddi and
Satyen Kale and
Sanjiv Kumar},
title = {On the Convergence of Adam and Beyond},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{Zeiler2012ADADELTAAA,
author = {Matthew D. Zeiler},
title = {ADADELTA:An Adaptive Learning Rate Method},
publisher = {arXiv preprint arXiv:1212.5701},
year = {2012}
}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 9------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 10------------------------------------------------------
@inproceedings{vaswani2017attention,
title={Attention is All You Need},
author={Ashish {Vaswani} and Noam {Shazeer} and Niki {Parmar} and Jakob {Uszkoreit} and Llion {Jones} and Aidan N. {Gomez} and Lukasz {Kaiser} and Illia {Polosukhin}},
publisher={International Conference on Neural Information Processing},
pages={5998--6008},
year={2017}
}
@inproceedings{DBLP:conf/acl/LiLWJXZLL20,
author = {Bei Li and
Hui Liu and
Ziyang Wang and
Yufan Jiang and
Tong Xiao and
Jingbo Zhu and
Tongran Liu and
Changliang Li},
title = {Does Multi-Encoder Help? {A} Case Study on Context-Aware Neural Machine
Translation},
pages = {3512--3518},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/emnlp/MiWI16,
author = {Haitao Mi and
Zhiguo Wang and
Abe Ittycheriah},
title = {Supervised Attentions for Neural Machine Translation},
pages = {2283--2288},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/coling/LiuUFS16,
author = {Lemao Liu and
Masao Utiyama and
Andrew M. Finch and
Eiichiro Sumita},
title = {Neural Machine Translation with Supervised Attention},
pages = {3093--3102},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{devlin-etal-2014-fast,
author = {Jacob Devlin and
Rabih Zbib and
Zhongqiang Huang and
Thomas Lamar and
Richard M. Schwartz and
John Makhoul},
title = {Fast and Robust Neural Network Joint Models for Statistical Machine
Translation},
pages = {1370--1380},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{Schwenk_continuousspace,
author = {Holger Schwenk},
title = {Continuous Space Translation Models for Phrase-Based Statistical Machine
Translation},
pages = {1071--1080},
publisher = {International Conference on Computational Linguistics},
year = {2012}
}
@inproceedings{kalchbrenner-blunsom-2013-recurrent,
author = {Nal Kalchbrenner and
Phil Blunsom},
title = {Recurrent Continuous Translation Models},
pages = {1700--1709},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@inproceedings{HochreiterThe,
author = {Sepp Hochreiter},
title = {The Vanishing Gradient Problem During Learning Recurrent Neural Nets
and Problem Solutions},
publisher = {International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems},
volume = {6},
number = {2},
pages = {107--116},
year = {1998}
}
@inproceedings{BENGIO1994Learning,
author = {Yoshua Bengio and
Patrice Y. Simard and
Paolo Frasconi},
title = {Learning long-term dependencies with gradient descent is difficult},
publisher = {IEEE Transportation Neural Networks},
volume = {5},
number = {2},
pages = {157--166},
year = {1994}
}
@inproceedings{StahlbergNeural,
title={Neural Machine Translation: A Review},
author={Felix Stahlberg},
publisher={Journal of Artificial Intelligence Research},
year={2020},
volume={69},
pages={343-418}
}
@inproceedings{Bentivogli2016NeuralVP,
author = {Luisa Bentivogli and
Arianna Bisazza and
Mauro Cettolo and
Marcello Federico},
title = {Neural versus Phrase-Based Machine Translation Quality: a Case Study},
pages = {257--267},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{Hassan2018AchievingHP,
author = {Hany Hassan and
Anthony Aue and
Chang Chen and
Vishal Chowdhary and
Jonathan Clark and
Christian Federmann and
Xuedong Huang and
Marcin Junczys-Dowmunt and
William Lewis and
Mu Li and
Shujie Liu and
Tie-Yan Liu and
Renqian Luo and
Arul Menezes and
Tao Qin and
Frank Seide and
Xu Tan and
Fei Tian and
Lijun Wu and
Shuangzhi Wu and
Yingce Xia and
Dongdong Zhang and
Zhirui Zhang and
Ming Zhou},
title = {Achieving Human Parity on Automatic Chinese to English News Translation},
publisher = {CoRR},
volume = {abs/1803.05567},
year = {2018},
}
@inproceedings{WangLearning,
author = {Qiang Wang and
Bei Li and
Tong Xiao and
Jingbo Zhu and
Changliang Li and
Derek F. Wong and
Lidia S. Chao},
title = {Learning Deep Transformer Models for Machine Translation},
pages = {1810--1822},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{Li2020NeuralMT,
author = {Yanyang Li and
Qiang Wang and
Tong Xiao and
Tongran Liu and
Jingbo Zhu},
title = {Neural Machine Translation with Joint Representation},
pages = {8285--8292},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2020}
}
@inproceedings{HochreiterLong,
author = {Hochreiter, Sepp and Schmidhuber, Jürgen},
year = {1997},
month = {12},
pages = {1735-80},
title = {Long Short-term Memory},
volume = {9},
publisher = {Neural Computation}
}
@inproceedings{Cho2014Learning,
author = {Kyunghyun Cho and
Bart van Merrienboer and
{\c{C}}aglar G{\"{u}}l{\c{c}}ehre and
Dzmitry Bahdanau and
Fethi Bougares and
Holger Schwenk and
Yoshua Bengio},
title = {Learning Phrase Representations using {RNN} Encoder-Decoder for Statistical
Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {1724--1734},
year = {2014}
}
@inproceedings{pmlr-v9-glorot10a,
author = {Xavier Glorot and
Yoshua Bengio},
title = {Understanding the difficulty of training deep feedforward neural networks},
publisher = {International Conference on Artificial Intelligence and Statistics},
volume = {9},
pages = {249--256},
year = {2010}
}
@inproceedings{xiao2017fast,
author = {Tong Xiao and
Jingbo Zhu and
Tongran Liu and
Chunliang Zhang},
title = {Fast Parallel Training of Neural Language Models},
publisher = {International Joint Conference on Artificial Intelligence},
pages = {4193--4199},
year = {2017}
}
@inproceedings{Gu2017NonAutoregressiveNM,
author = {Jiatao Gu and
James Bradbury and
Caiming Xiong and
Victor O. K. Li and
Richard Socher},
title = {Non-Autoregressive Neural Machine Translation},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{li-etal-2018-simple,
author = {Yanyang Li and
Tong Xiao and
Yinqiao Li and
Qiang Wang and
Changming Xu and
Jingbo Zhu},
title = {A Simple and Effective Approach to Coverage-Aware Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {292--297},
year = {2018}
}
@inproceedings{TuModeling,
author = {Zhaopeng Tu and
Zhengdong Lu and
Yang Liu and
Xiaohua Liu and
Hang Li},
title = {Modeling Coverage for Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:journals/corr/SennrichFCBHHJL17,
author = {Rico Sennrich and
Orhan Firat and
Kyunghyun Cho and
Barry Haddow and
Alexandra Birch and
Julian Hitschler and
Marcin Junczys-Dowmunt and
Samuel L{\"{a}}ubli and
Antonio Valerio Miceli Barone and
Jozef Mokry and
Maria Nadejde},
title = {Nematus: a Toolkit for Neural Machine Translation},
publisher = {Annual Conference of the European Association for Machine Translation},
pages = {65--68},
year = {2017}
}
@inproceedings{DBLP:journals/corr/abs-1905-13324,
author = {Biao Zhang and
Rico Sennrich},
title = {A Lightweight Recurrent Network for Sequence Modeling},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {1538--1548},
year = {2019}
}
@inproceedings{Lei2017TrainingRA,
author = {Tao Lei and
Yu Zhang and
Yoav Artzi},
title = {Training RNNs as Fast as CNNs},
publisher = {CoRR},
volume = {abs/1709.02755},
year = {2017}
}
@inproceedings{Zhang2018SimplifyingNM,
author = {Biao Zhang and
Deyi Xiong and
Jinsong Su and
Qian Lin and
Huiji Zhang},
title = {Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated
Recurrent Networks},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {4273--4283},
year = {2018}
}
@inproceedings{Liu_2019_CVPR,
author = {Shikun Liu and
Edward Johns and
Andrew J. Davison},
title = {End-To-End Multi-Task Learning With Attention},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
pages = {1871--1880},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-1811-00498,
author = {Ra{\'{u}}l V{\'{a}}zquez and
Alessandro Raganato and
J{\"{o}}rg Tiedemann and
Mathias Creutz},
title = {Multilingual {NMT} with a Language-Independent Attention Bridge},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {33--39},
year = {2019}
}
@inproceedings{MoradiInterrogating,
author = {Pooya Moradi and
Nishant Kambhatla and
Anoop Sarkar},
title = {Interrogating the Explanatory Power of Attention in Neural Machine
Translation},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {221--230},
year = {2019}
}
@inproceedings{WangNeural,
author = {Xing Wang and
Zhengdong Lu and
Zhaopeng Tu and
Hang Li and
Deyi Xiong and
Min Zhang},
title = {Neural Machine Translation Advised by Statistical Machine Translation},
publisher = {AAAI Conference on Artificial Intelligence},
pages = {3330--3336},
year = {2017}
}
@inproceedings{Xiao2019SharingAW,
author = {Tong Xiao and
Yinqiao Li and
Jingbo Zhu and
Zhengtao Yu and
Tongran Liu},
title = {Sharing Attention Weights for Fast Transformer},
publisher = {International Joint Conference on Artificial Intelligence},
pages = {5292--5298},
year = {2019}
}
@inproceedings{Yang2017TowardsBH,
author = {Baosong Yang and
Derek F. Wong and
Tong Xiao and
Lidia S. Chao and
Jingbo Zhu},
title = {Towards Bidirectional Hierarchical Representations for Attention-based
Neural Machine Translation},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {1432--1441},
year = {2017}
}
@inproceedings{Wang2019TreeTI,
author = {Yau-Shian Wang and
Hung-yi Lee and
Yun-Nung Chen},
title = {Tree Transformer: Integrating Tree Structures into Self-Attention},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {1061--1070},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-1809-01854,
author = {Jetic Gu and
Hassan S. Shavarani and
Anoop Sarkar},
title = {Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {401--413},
year = {2018}
}
@inproceedings{DBLP:journals/corr/abs-1808-09374,
author = {Xinyi Wang and
Hieu Pham and
Pengcheng Yin and
Graham Neubig},
title = {A Tree-based Decoder for Neural Machine Translation},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {4772--4777},
year = {2018}
}
@inproceedings{DBLP:journals/corr/ZhangZ16c,
author = {Jiajun Zhang and
Chengqing Zong},
title = {Bridging Neural Machine Translation and Bilingual Dictionaries},
publisher = {CoRR},
volume = {abs/1610.07272},
year = {2016}
}
@inproceedings{Dai2019TransformerXLAL,
author = {Zihang Dai and
Zhilin Yang and
Yiming Yang and
Jaime G. Carbonell and
Quoc V. Le and
Ruslan Salakhutdinov},
title = {Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {2978--2988},
year = {2019}
}
@inproceedings{li-etal-2019-word,
author = {Xintong Li and
Guanlin Li and
Lemao Liu and
Max Meng and
Shuming Shi},
title = {On the Word Alignment from Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {1293--1303},
year = {2019}
}
@inproceedings{Werlen2018DocumentLevelNM,
author = {Lesly Miculicich Werlen and
Dhananjay Ram and
Nikolaos Pappas and
James Henderson},
title = {Document-Level Neural Machine Translation with Hierarchical Attention
Networks},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {2947--2954},
year = {2018}
}
@inproceedings{DBLP:journals/corr/abs-1805-10163,
author = {Elena Voita and
Pavel Serdyukov and
Rico Sennrich and
Ivan Titov},
title = {Context-Aware Neural Machine Translation Learns Anaphora Resolution},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {1264--1274},
year = {2018}
}
@inproceedings{DBLP:journals/corr/abs-1906-00532,
author = {Aishwarya Bhandare and
Vamsi Sripathi and
Deepthi Karkada and
Vivek Menon and
Sun Choi and
Kushal Datta and
Vikram Saletore},
title = {Efficient 8-Bit Quantization of Transformer Neural Machine Language
Translation Model},
publisher = {CoRR},
volume = {abs/1906.00532},
year = {2019}
}
@inproceedings{Zhang2018SpeedingUN,
author = {Wen Zhang and
Liang Huang and
Yang Feng and
Lei Shen and
Qun Liu},
title = {Speeding Up Neural Machine Translation Decoding by Cube Pruning},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {4284--4294},
year = {2018}
}
@inproceedings{DBLP:journals/corr/SeeLM16,
author = {Abigail See and
Minh-Thang Luong and
Christopher D. Manning},
title = {Compression of Neural Machine Translation Models via Pruning},
publisher = {International Conference on Computational Linguistics},
pages = {291--301},
year = {2016}
}
@inproceedings{DBLP:journals/corr/ChenLCL17,
author = {Yun Chen and
Yang Liu and
Yong Cheng and
Victor O. K. Li},
title = {A Teacher-Student Framework for Zero-Resource Neural Machine Translation},
pages = {1925--1935},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{Hinton2015Distilling,
author = {Geoffrey Hinton and
Oriol Vinyals and
Jeffrey Dean},
title = {Distilling the Knowledge in a Neural Network},
publisher = {CoRR},
volume = {abs/1503.02531},
year = {2015}
}
@inproceedings{Ott2018ScalingNM,
title={Scaling Neural Machine Translation},
author={Myle Ott and Sergey Edunov and David Grangier and Michael Auli},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2018}
}
@inproceedings{Lin2020TowardsF8,
author = {Ye Lin and
Yanyang Li and
Tengbo Liu and
Tong Xiao and
Tongran Liu and
Jingbo Zhu},
title = {Towards Fully 8-bit Integer Inference for the Transformer Model},
pages = {3759--3765},
publisher = {International Joint Conference on Artificial Intelligence},
year = {2020}
}
@inproceedings{kim-rush-2016-sequence,
author = {Yoon Kim and
Alexander M. Rush},
title = {Sequence-Level Knowledge Distillation},
pages = {1317--1327},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2016}
}
@inproceedings{Akaike1969autoregressive,
author = {Hirotugu Akaike},
title = {Fitting autoregressive models for prediction},
publisher = {Annals of the institute of Statistical Mathematics},
volume = {21(1)},
year = {2015},
pages = {243--247},
}
@inproceedings{Chen2018TheBO,
author = {Mia Xu Chen and
Orhan Firat and
Ankur Bapna and
Melvin Johnson and
Wolfgang Macherey and
George F. Foster and
Llion Jones and
Mike Schuster and
Noam Shazeer and
Niki Parmar and
Ashish Vaswani and
Jakob Uszkoreit and
Lukasz Kaiser and
Zhifeng Chen and
Yonghui Wu and
Macduff Hughes},
title = {The Best of Both Worlds: Combining Recent Advances in Neural Machine
Translation},
pages = {76--86},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{He2018LayerWiseCB,
title={Layer-Wise Coordination between Encoder and Decoder for Neural Machine Translation},
author={Tianyu He and Xu Tan and Yingce Xia and Di He and Tao Qin and Zhibo Chen and Tie-Yan Liu},
publisher={Conference on Neural Information Processing Systems},
year={2018}
}
@inproceedings{cho-etal-2014-properties,
author = {Kyunghyun Cho and
Bart van Merrienboer and
Dzmitry Bahdanau and
Yoshua Bengio},
title = {On the Properties of Neural Machine Translation: Encoder-Decoder Approaches},
pages = {103--111},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/acl/JeanCMB15,
author = {S{\'{e}}bastien Jean and
KyungHyun Cho and
Roland Memisevic and
Yoshua Bengio},
title = {On Using Very Large Target Vocabulary for Neural Machine Translation},
pages = {1--10},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:journals/corr/LuongPM15,
author = {Thang Luong and
Hieu Pham and
Christopher D. Manning},
title = {Effective Approaches to Attention-based Neural Machine Translation},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {1412--1421},
year = {2015}
}
@inproceedings{He2016ImprovedNM,
author = {Wei He and
Zhongjun He and
Hua Wu and
Haifeng Wang},
title = {Improved Neural Machine Translation with {SMT} Features},
pages = {151--157},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2016}
}
@inproceedings{zhang-etal-2017-prior,
title = {Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization},
author = {Zhang, Jiacheng and
Liu, Yang and
Luan, Huanbo and
Xu, Jingfang and
Sun, Maosong},
year = {2017},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {1514--1523},
}
@inproceedings{duan-etal-2020-bilingual,
author = {Xiangyu Duan and
Baijun Ji and
Hao Jia and
Min Tan and
Min Zhang and
Boxing Chen and
Weihua Luo and
Yue Zhang},
title = {Bilingual Dictionary Based Neural Machine Translation without Using
Parallel Sentences},
pages = {1570--1579},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{cao-xiong-2018-encoding,
author = {Qian Cao and
Deyi Xiong},
title = {Encoding Gated Translation Memory into Neural Machine Translation},
pages = {3042--3047},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{yang-etal-2016-hierarchical,
author = {Zichao Yang and
Diyi Yang and
Chris Dyer and
Xiaodong He and
Alexander J. Smola and
Eduard H. Hovy},
title = {Hierarchical Attention Networks for Document Classification},
pages = {1480--1489},
publisher = {Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2016}
}
%%%%% chapter 10------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 11------------------------------------------------------
@inproceedings{DBLP:journals/pami/RenHG017,
author = {Shaoqing Ren and
Kaiming He and
Ross Girshick and
Jian Sun},
title = {Faster {R-CNN:} Towards Real-Time Object Detection with Region Proposal
Networks},
publisher = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence},
volume = {39},
number = {6},
pages = {1137--1149},
year = {2017}
}
@inproceedings{DBLP:conf/eccv/LiuAESRFB16,
author = {Wei Liu and
Dragomir Anguelov and
Dumitru Erhan and
Christian Szegedy and
Scott Reed and
Cheng-Yang Fu and
Alexander C. Berg},
title = {{SSD:} Single Shot MultiBox Detector},
publisher = {European Conference on Computer Vision},
volume = {9905},
pages = {21--37},
year = {2016}
}
@inproceedings{devlin-etal-2014-fast,
author = {Jacob Devlin and
Rabih Zbib and
Zhongqiang Huang and
Thomas Lamar and
Richard M. Schwartz and
John Makhoul},
title = {Fast and Robust Neural Network Joint Models for Statistical Machine
Translation},
pages = {1370--1380},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/acl/WangLLJL15,
author = {Mingxuan Wang and
Zhengdong Lu and
Hang Li and
Wenbin Jiang and
Qun Liu},
title = {genCNN: {A} Convolutional Architecture for Word Sequence Prediction},
pages = {1567--1576},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:conf/icassp/ZhangCJ17,
author = {Yu Zhang and
William Chan and
Navdeep Jaitly},
title = {Very deep convolutional networks for end-to-end speech recognition},
pages = {4845--4849},
publisher = {International Conference on Acoustics, Speech and Signal Processing},
year = {2017}
}
@inproceedings{DBLP:conf/icassp/DengAY13,
author = {Li Deng and
Ossama Abdel-Hamid and
Dong Yu},
title = {A deep convolutional neural network using heterogeneous pooling for
trading acoustic invariance with phonetic confusion},
pages = {6669--6673},
publisher = {International Conference on Acoustics, Speech and Signal Processing},
year = {2013}
}
@inproceedings{DBLP:journals/corr/LuongPM15,
author = {Thang Luong and
Hieu Pham and
Christopher D. Manning},
title = {Effective Approaches to Attention-based Neural Machine Translation},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {1412--1421},
year = {2015}
}
@inproceedings{DBLP:conf/acl-codeswitch/WangCK18,
author = {Changhan Wang and
Kyunghyun Cho and
Douwe Kiela},
title = {Code-Switched Named Entity Recognition with Embedding Attention},
pages = {154--158},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/LiDWCM17,
author = {Peng-Hsuan Li and
Ruo-Ping Dong and
Yu-Siang Wang and
Ju-Chieh Chou and
Wei-Yun Ma},
title = {Leveraging Linguistic Structures for Named Entity Recognition with
Bidirectional Recursive Neural Networks},
pages = {2664--2669},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/acl/MaH16,
author = {Xuezhe Ma and
Eduard H. Hovy},
title = {End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/emnlp/StrubellVBM17,
author = {Emma Strubell and
Patrick Verga and
David Belanger and
Andrew Mccallum},
title = {Fast and Accurate Entity Recognition with Iterated Dilated Convolutions},
pages = {2670--2680},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/cncl/ZhouZXQBX17,
author = {Peng Zhou and
Suncong Zheng and
Jiaming Xu and
Zhenyu Qi and
Hongyun Bao and
Bo Xu},
title = {Joint Extraction of Multiple Relations and Entities by Using a Hybrid
Neural Network},
volume = {10565},
pages = {135--146},
publisher = {Springer},
year = {2017}
}
@inproceedings{2011Natural,
title={Natural Language Processing (almost) from Scratch},
author={ Collobert, Ronan and Weston, Jason and Bottou, Léon and Karlen, Michael and Kavukcuoglu, Koray and Kuksa, Pavel },
publisher={Journal of Machine Learning Research},
volume={12},
number={1},
pages={2493-2537},
year={2011},
}
@inproceedings{DBLP:conf/acl/NguyenG15,
author = {Thien Huu Nguyen and
Ralph Grishman},
title = {Event Detection and Domain Adaptation with Convolutional Neural Networks},
pages = {365--371},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:conf/aaai/LaiXLZ15,
author = {Siwei Lai and
Liheng Xu and
Kang Liu and
Jun Zhao},
title = {Recurrent Convolutional Neural Networks for Text Classification},
pages = {2267--2273},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2015}
}
@inproceedings{DBLP:conf/acl/ChenXLZ015,
author = {Yubo Chen and
Liheng Xu and
Kang Liu and
Daojian Zeng and
Jun Zhao},
title = {Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks},
pages = {167--176},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:conf/emnlp/LeiBJ15,
author = {Tao Lei and
Regina Barzilay and
Tommi S. Jaakkola},
title = {Molding CNNs for text: non-linear, non-consecutive convolutions},
pages = {1565--1575},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2015}
}
@inproceedings{DBLP:conf/naacl/Johnson015,
author = {Rie Johnson and
Tong Zhang},
title = {Effective Use of Word Order for Text Categorization with Convolutional
Neural Networks},
pages = {103--112},
publisher = {Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:conf/naacl/NguyenG15,
author = {Thien Huu Nguyen and
Ralph Grishman},
title = {Relation Extraction: Perspective from Convolutional Neural Networks},
pages = {39--48},
publisher = {Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{StahlbergNeural,
title={Neural Machine Translation: A Review},
author={Felix Stahlberg},
publisher={Journal of Artificial Intelligence Research},
year={2020},
volume={69},
pages={343-418}
}
@inproceedings{Sennrich2016ImprovingNM,
author = {Rico Sennrich and
Barry Haddow and
Alexandra Birch},
title = {Improving Neural Machine Translation Models with Monolingual Data},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{bahdanau2014neural,
author = {Dzmitry Bahdanau and
Kyunghyun Cho and
Yoshua Bengio},
title = {Neural Machine Translation by Jointly Learning to Align and Translate},
publisher = {International Conference on Learning Representations},
year = {2015}
}
@inproceedings{Waibel1989PhonemeRU,
title={Phoneme recognition using time-delay neural networks},
author={Alexander Waibel and Toshiyuki Hanazawa and Geoffrey Hinton and Kiyohiro Shikano and Kevin J. Lang},
publisher={IEEE Transactions on Acoustics, Speech, and Signal Processing},
year={1989},
volume={37},
pages={328-339}
}
@inproceedings{LeCun1989BackpropagationAT,
title={Backpropagation Applied to Handwritten Zip Code Recognition},
author={Yann Lecun and Bernhard Boser and John Denker and Don Henderson and Richard E.Howard and Wayne E. Hubbard and Larry Jackel},
publisher={Neural Computation},
year={1989},
volume={1},
pages={541-551}
}
@inproceedings{726791,
author={Yann {Lecun} and Leon {Bottou} and Yoshua {Bengio} and Patrick {Haffner}},
publisher={Proceedings of the IEEE},
title={Gradient-based learning applied to document recognition},
year={1998},
volume={86},
number={11},
pages={2278-2324}
}
@inproceedings{DBLP:journals/corr/HeZRS15,
author = {Kaiming He and
Xiangyu Zhang and
Shaoqing Ren and
Jian Sun},
title = {Deep Residual Learning for Image Recognition},
publisher = {{IEEE} Conference on Computer Vision and Pattern Recognition},
pages = {770--778},
year = {2016}
}
@inproceedings{DBLP:conf/cvpr/HuangLMW17,
author = {Gao Huang and
Zhuang Liu and
Laurens van der Maaten and
Kilian Q. Weinberger},
title = {Densely Connected Convolutional Networks},
pages = {2261--2269},
publisher = {{IEEE} Conference on Computer Vision and Pattern Recognition},
year = {2017}
}
@inproceedings{Girshick2015FastR,
title={Fast R-CNN},
author={Ross Girshick},
publisher={International Conference on Computer Vision},
year={2015},
pages={1440-1448}
}
@inproceedings{He2020MaskR,
title={Mask R-CNN},
author={Kaiming He and Georgia Gkioxari and Piotr Doll{\'a}r and Ross B. Girshick},
publisher={International Conference on Computer Vision},
pages={2961--2969},
year={2017}
}
@inproceedings{Kalchbrenner2014ACN,
title={A Convolutional Neural Network for Modelling Sentences},
author={Nal Kalchbrenner and Edward Grefenstette and Phil Blunsom},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={655--665},
year={2014}
}
@inproceedings{Kim2014ConvolutionalNN,
title={Convolutional Neural Networks for Sentence Classification},
author={Yoon Kim},
publisher={Conference on Empirical Methods in Natural Language Processing},
pages = {1746--1751},
year={2014}
}
@inproceedings{Ma2015DependencybasedCN,
title={Dependency-based Convolutional Neural Networks for Sentence Embedding},
author = {Mingbo Ma and
Liang Huang and
Bowen Zhou and
Bing Xiang},
pages = {174--179},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2015}
}
@inproceedings{Santos2014DeepCN,
title={Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts},
author = {C{\'{\i}}cero Nogueira dos Santos and
Maira Gatti},
pages = {69--78},
publisher = {International Conference on Computational Linguistics},
year={2014}
}
@inproceedings{Dauphin2017LanguageMW,
title={Language Modeling with Gated Convolutional Networks},
author = {Yann N. Dauphin and
Angela Fan and
Michael Auli and
David Grangier},
publisher={International Conference on Machine Learning},
volume = {70},
pages = {933--941},
year={2017}
}
@inproceedings{Gehring2017ACE,
title={A Convolutional Encoder Model for Neural Machine Translation},
author = {Jonas Gehring and
Michael Auli and
David Grangier and
Yann N. Dauphin},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages = {123--135},
year={2017}
}
@inproceedings{DBLP:journals/corr/GehringAGYD17,
author = {Jonas Gehring and
Michael Auli and
David Grangier and
Denis Yarats and
Yann N. Dauphin},
title = {Convolutional Sequence to Sequence Learning},
publisher = {International Conference on Machine Learning},
volume = {70},
pages = {1243--1252},
year = {2017}
}
@inproceedings{Kaiser2018DepthwiseSC,
title={Depthwise Separable Convolutions for Neural Machine Translation},
author = {Lukasz Kaiser and
Aidan N. Gomez and
Fran{\c{c}}ois Chollet},
publisher = {International Conference on Learning Representations},
year={2018},
}
@inproceedings{Wu2019PayLA,
author = {Felix Wu and
Angela Fan and
Alexei Baevski and
Yann N. Dauphin and
Michael Auli},
title = {Pay Less Attention with Lightweight and Dynamic Convolutions},
publisher = {International Conference on Learning Representations},
year = {2019}
}
@inproceedings{kalchbrenner-blunsom-2013-recurrent,
author = {Nal Kalchbrenner and
Phil Blunsom},
title = {Recurrent Continuous Translation Models},
pages = {1700--1709},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2013}
}
@inproceedings{Wu2016GooglesNM,
title={Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation},
author = {Yonghui Wu and
Mike Schuster and
Zhifeng Chen and
Quoc V. Le and
Mohammad Norouzi and
Wolfgang Macherey and
Maxim Krikun and
Yuan Cao and
Qin Gao and
Klaus Macherey and
Jeff Klingner and
Apurva Shah and
Melvin Johnson and
Xiaobing Liu and
Lukasz Kaiser and
Stephan Gouws and
Yoshikiyo Kato and
Taku Kudo and
Hideto Kazawa and
Keith Stevens and
George Kurian and
Nishant Patil and
Wei Wang and
Cliff Young and
Jason Smith and
Jason Riesa and
Alex Rudnick and
Oriol Vinyals and
Greg Corrado and
Macduff Hughes and
Jeffrey Dean},
publisher = {CoRR},
year={2016},
volume={abs/1609.08144}
}
@inproceedings{DBLP:journals/corr/HeZRS15,
author = {Kaiming He and
Xiangyu Zhang and
Shaoqing Ren and
Jian Sun},
title = {Deep Residual Learning for Image Recognition},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
pages = {770--778},
year = {2016},
}
@inproceedings{Sukhbaatar2015EndToEndMN,
title={End-To-End Memory Networks},
author = {Sainbayar Sukhbaatar and
Arthur Szlam and
Jason Weston and
Rob Fergus},
publisher={Conference on Neural Information Processing Systems},
pages = {2440--2448},
year={2015}
}
@inproceedings{Islam2020HowMP,
author = {Md. Amirul Islam and
Sen Jia and
Neil Bruce},
title = {How much Position Information Do Convolutional Neural Networks Encode?},
publisher = {International Conference on Learning Representations},
year = {2020},
}
@inproceedings{Sutskever2013OnTI,
title={On the importance of initialization and momentum in deep learning},
author = {Ilya Sutskever and
James Martens and
George E. Dahl and
Geoffrey Hinton},
publisher = {International Conference on Machine Learning},
pages = {1139--1147},
year={2013}
}
@inproceedings{Bengio2013AdvancesIO,
title={Advances in optimizing recurrent networks},
author={Yoshua Bengio and Nicolas Boulanger-Lewandowski and Razvan Pascanu},
publisher={IEEE Transactions on Acoustics, Speech, and Signal Processing},
year={2013},
pages={8624-8628}
}
@inproceedings{JMLR:v15:srivastava14a,
author = {Nitish Srivastava and Geoffrey Hinton and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov},
title = {Dropout: A Simple Way to Prevent Neural Networks from Overfitting},
publisher = {Journal of Machine Learning Research},
year = {2014},
volume = {15},
pages = {1929-1958},
}
@inproceedings{Chollet2017XceptionDL,
title={Xception: Deep Learning with Depthwise Separable Convolutions},
author = {Fran{\c{c}}ois Chollet},
publisher={IEEE Conference on Computer Vision and Pattern Recognition},
year={2017},
pages={1800-1807}
}
@inproceedings{Howard2017MobileNetsEC,
title={MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications},
author = {Andrew Howard and
Menglong Zhu and
Bo Chen and
Dmitry Kalenichenko and
Weijun Wang and
Tobias Weyand and
Marco Andreetto and
Hartwig Adam},
journal={CoRR},
year={2017},
}
@inproceedings{sifre2014rigid,
title={Rigid-motion scattering for image classification},
author={Sifre, Laurent and Mallat, St{\'e}phane},
year={2014},
publisher={Citeseer}
}
@inproceedings{Taigman2014DeepFaceCT,
title={DeepFace: Closing the Gap to Human-Level Performance in Face Verification},
author={Yaniv Taigman and Ming Yang and Marc'Aurelio Ranzato and Lior Wolf},
publisher={IEEE Conference on Computer Vision and Pattern Recognition},
year={2014},
pages={1701-1708}
}
@inproceedings{Chen2015LocallyconnectedAC,
title={Locally-connected and convolutional neural networks for small footprint speaker recognition},
author = {Yu-hsin Chen and
Ignacio Lopez-Moreno and
Tara Sainath and
Mirk{\'{o}} Visontai and
Raziel Alvarez and
Carolina Parada},
publisher={Conference of the International Speech Communication Association},
pages = {1136--1140},
year={2015}
}
@inproceedings{Chen2020DynamicCA,
title={Dynamic Convolution: Attention Over Convolution Kernels},
author = {Yinpeng Chen and
Xiyang Dai and
Mengchen Liu and
Dongdong Chen and
Lu Yuan and
Zicheng Liu},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year={2020},
pages={11027-11036}
}
%%%%% chapter 11------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 12------------------------------------------------------
@inproceedings{DBLP:conf/coling/ZengLLZZ14,
author = {Daojian Zeng and
Kang Liu and
Siwei Lai and
Guangyou Zhou and
Jun Zhao},
title = {Relation Classification via Convolutional Deep Neural Network},
pages = {2335--2344},
publisher = {International Conference on Computational Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/acl/JohnsonZ17,
author = {Rie Johnson and
Tong Zhang},
title = {Deep Pyramid Convolutional Neural Networks for Text Categorization},
pages = {562--570},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/interspeech/GulatiQCPZYHWZW20,
author = {Anmol Gulati and
James Qin and
Chung-Cheng Chiu and
Niki Parmar and
Yu Zhang and
Jiahui Yu and
Wei Han and
Shibo Wang and
Zhengdong Zhang and
Yonghui Wu and
Ruoming Pang},
title = {Conformer: Convolution-augmented Transformer for Speech Recognition},
pages = {5036--5040},
publisher = {International Speech Communication Association},
year = {2020}
}
@inproceedings{DBLP:conf/icassp/DongXX18,
author = {Linhao Dong and
Shuang Xu and
Bo Xu},
title = {Speech-Transformer: {A} No-Recurrence Sequence-to-Sequence Model for
Speech Recognition},
pages = {5884--5888},
publisher = {International Conference on Acoustics, Speech and Signal Processing},
year = {2018}
}
@inproceedings{DBLP:journals/corr/abs-1802-05751,
author = {Niki Parmar and
Ashish Vaswani and
Jakob Uszkoreit and
Lukasz Kaiser and
Noam Shazeer and
Alexander Ku},
title = {Image Transformer},
publisher = {CoRR},
volume = {abs/1802.05751},
year = {2018}
}
@inproceedings{vaswani2017attention,
title={Attention is All You Need},
author={Ashish {Vaswani} and Noam {Shazeer} and Niki {Parmar} and Jakob {Uszkoreit} and Llion {Jones} and Aidan N. {Gomez} and Lukasz {Kaiser} and Illia {Polosukhin}},
publisher={International Conference on Neural Information Processing},
pages={5998--6008},
year={2017}
}
@inproceedings{DBLP:conf/iclr/WuLLLH20,
author = {Zhanghao Wu and
Zhijian Liu and
Ji Lin and
Yujun Lin and
Song Han},
title = {Lite Transformer with Long-Short Range Attention},
publisher = {International Conference on Learning Representations},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-1905-09418,
author = {Elena Voita and
David Talbot and
Fedor Moiseev and
Rico Sennrich and
Ivan Titov},
title = {Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy
Lifting, the Rest Can Be Pruned},
pages = {5797--5808},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019},
}
@inproceedings{DBLP:journals/corr/LinFSYXZB17,
author = {Zhouhan Lin and
Minwei Feng and
C{\'{\i}}cero Nogueira dos Santos and
Mo Yu and
Bing Xiang and
Bowen Zhou and
Yoshua Bengio},
title = {A Structured Self-Attentive Sentence Embedding},
publisher = {International Conference on Learning Representations},
year = {2017},
}
@inproceedings{Shaw2018SelfAttentionWR,
author = {Peter Shaw and
Jakob Uszkoreit and
Ashish Vaswani},
title = {Self-Attention with Relative Position Representations},
publisher = {Proceedings of the Human Language Technology Conference of
the North American Chapter of the Association for Computational Linguistics},
pages = {464--468},
year = {2018},
}
@inproceedings{DBLP:journals/corr/HeZRS15,
author = {Kaiming He and
Xiangyu Zhang and
Shaoqing Ren and
Jian Sun},
title = {Deep Residual Learning for Image Recognition},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
pages = {770--778},
year = {2016},
}
@inproceedings{JMLR:v15:srivastava14a,
author = {Nitish Srivastava and Geoffrey Hinton and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov},
title = {Dropout: A Simple Way to Prevent Neural Networks from Overfitting},
publisher = {Journal of Machine Learning Research},
year = {2014},
volume = {15},
pages = {1929-1958},
}
@inproceedings{Szegedy_2016_CVPR,
author = {Christian Szegedy and
Vincent Vanhoucke and
Sergey Ioffe and
Jonathon Shlens and
Zbigniew Wojna},
title = {Rethinking the Inception Architecture for Computer Vision},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
pages = {2818--2826},
year = {2016},
}
@inproceedings{DBLP:journals/corr/abs-1805-00631,
author = {Biao Zhang and
Deyi Xiong and
Jinsong Su},
title = {Accelerating Neural Transformer via an Average Attention Network},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {1789--1798},
year = {2018},
}
@inproceedings{DBLP:journals/corr/CourbariauxB16,
author = {Matthieu Courbariaux and
Yoshua Bengio},
title = {BinaryNet: Training Deep Neural Networks with Weights and Activations
Constrained to +1 or -1},
publisher = {CoRR},
volume = {abs/1602.02830},
year = {2016},
}
@inproceedings{Wu2019PayLA,
author = {Felix Wu and
Angela Fan and
Alexei Baevski and
Yann N. Dauphin and
Michael Auli},
title = {Pay Less Attention with Lightweight and Dynamic Convolutions},
publisher = {International Conference on Learning Representations},
year = {2019},
}
@inproceedings{dai-etal-2019-transformer,
author = {Zihang Dai and
Zhilin Yang and
Yiming Yang and
Jaime G. Carbonell and
Quoc Viet Le and
Ruslan Salakhutdinov},
title = {Transformer-XL: Attentive Language Models beyond a Fixed-Length Context},
pages = {2978--2988},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{Liu2020LearningTE,
title={Learning to Encode Position for Transformer with Continuous Dynamical Model},
author={Xuanqing Liu and Hsiang-Fu Yu and Inderjit Dhillon and Cho-Jui Hsieh},
publisher={ArXiv},
year={2020},
volume={abs/2003.09229}
}
@inproceedings{Jawahar2019WhatDB,
title={What Does BERT Learn about the Structure of Language?},
author={Ganesh Jawahar and Beno{\^{\i}}t Sagot and Djam{\'e} Seddah},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2019}
}
@inproceedings{Yang2018ModelingLF,
author = {Baosong Yang and
Zhaopeng Tu and
Derek F. Wong and
Fandong Meng and
Lidia S. Chao and
Tong Zhang},
title = {Modeling Localness for Self-Attention Networks},
pages = {4449--4458},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:journals/corr/abs-1904-03107,
author = {Baosong Yang and
Longyue Wang and
Derek F. Wong and
Lidia S. Chao and
Zhaopeng Tu},
title = {Convolutional Self-Attention Networks},
pages = {4040--4045},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019},
}
@inproceedings{Wang2018MultilayerRF,
title={Multi-layer Representation Fusion for Neural Machine Translation},
author={Qiang Wang and Fuxue Li and Tong Xiao and Yanyang Li and Yinqiao Li and Jingbo Zhu},
publisher={International Conference on Computational Linguistics},
year={2018},
volume={abs/2002.06714}
}
@inproceedings{Bapna2018TrainingDN,
author = {Ankur Bapna and
Mia Xu Chen and
Orhan Firat and
Yuan Cao and
Yonghui Wu},
title = {Training Deeper Neural Machine Translation Models with Transparent
Attention},
pages = {3028--3033},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{Dou2018ExploitingDR,
author = {Zi-Yi Dou and
Zhaopeng Tu and
Xing Wang and
Shuming Shi and
Tong Zhang},
title = {Exploiting Deep Representations for Neural Machine Translation},
pages = {4253--4262},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{Wang2019ExploitingSC,
title={Exploiting Sentential Context for Neural Machine Translation},
author={Xing Wang and Zhaopeng Tu and Longyue Wang and Shuming Shi},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2019}
}
@inproceedings{Dou2019DynamicLA,
author = {Zi-Yi Dou and
Zhaopeng Tu and
Xing Wang and
Longyue Wang and
Shuming Shi and
Tong Zhang},
title = {Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement},
pages = {86--93},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2019}
}
@inproceedings{Wei2020MultiscaleCD,
title={Multiscale Collaborative Deep Models for Neural Machine Translation},
author={Xiangpeng Wei and Heng Yu and Yue Hu and Yue Zhang and Rongxiang Weng and Weihua Luo},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2020}
}
@inproceedings{Vaswani2018Tensor2TensorFN,
author = {Ashish Vaswani and
Samy Bengio and
Eugene Brevdo and
Fran{\c{c}}ois Chollet and
Aidan N. Gomez and
Stephan Gouws and
Llion Jones and
Lukasz Kaiser and
Nal Kalchbrenner and
Niki Parmar and
Ryan Sepassi and
Noam Shazeer and
Jakob Uszkoreit},
title = {Tensor2Tensor for Neural Machine Translation},
pages = {193--199},
publisher = {Association for Machine Translation in the Americas},
year = {2018}
}
@inproceedings{Kitaev2020ReformerTE,
author = {Nikita Kitaev and
Lukasz Kaiser and
Anselm Levskaya},
title = {Reformer: The Efficient Transformer},
publisher = {International Conference on Learning Representations},
year = {2020}
}
@inproceedings{Lin2020WeightDT,
title={Weight Distillation: Transferring the Knowledge in Neural Network Parameters},
author={Ye Lin and Yanyang Li and Ziyang Wang and Bei Li and Quan Du and Tong Xiao and Jingbo Zhu},
publisher={ArXiv},
year={2020},
volume={abs/2009.09152}
}
@inproceedings{li2020shallow,
title={Shallow-to-Deep Training for Neural Machine Translation},
author={Li, Bei and Wang, Ziyang and Liu, Hui and Jiang, Yufan and Du, Quan and Xiao, Tong and Wang, Huizhen and Zhu, Jingbo},
publisher={Conference on Empirical Methods in Natural Language Processing},
year={2020}
}
%%%%% chapter 12------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 13------------------------------------------------------
@inproceedings{garcia-martinez2016factored,
title={Factored Neural Machine Translation Architectures},
author={Mercedes {Garcia-Martinez} and Loïc {Barrault} and Fethi {Bougares}},
publisher={International Workshop on Spoken Language Translation (IWSLT'16)},
notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2949810612},
year={2016}
}
@inproceedings{DBLP:conf/acl/Kudo18,
author = {Taku Kudo},
title = {Subword Regularization: Improving Neural Network Translation Models
with Multiple Subword Candidates},
pages = {66--75},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:journals/jmlr/RaffelSRLNMZLL20,
author = {Colin Raffel and
Noam Shazeer and
Adam Roberts and
Katherine Lee and
Sharan Narang and
Michael Matena and
Yanqi Zhou and
Wei Li and
Peter J. Liu},
title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text
Transformer},
publisher = {Journal of Machine Learning Reseach},
volume = {21},
pages = {140:1--140:67},
year = {2020}
}
@inproceedings{DBLP:conf/icassp/SchusterN12,
author = {Mike Schuster and
Kaisuke Nakajima},
title = {Japanese and Korean voice search},
pages = {5149--5152},
publisher = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2012}
}
@inproceedings{JMLR:v15:srivastava14a,
author = {Nitish Srivastava and Geoffrey Hinton and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov},
title = {Dropout: A Simple Way to Prevent Neural Networks from Overfitting},
publisher = {Journal of Machine Learning Research},
year = {2014},
volume = {15},
pages = {1929-1958},
}
@inproceedings{DBLP:conf/amta/MullerRS20,
author = {Mathias M{\"{u}}ller and
Annette Rios and
Rico Sennrich},
title = {Domain Robustness in Neural Machine Translation},
pages = {151--164},
publisher = {Association for Machine Translation in the Americas},
year = {2020}
}
@inproceedings{DBLP:conf/sp/Carlini017,
author = {Nicholas Carlini and
David A. Wagner},
title = {Towards Evaluating the Robustness of Neural Networks},
pages = {39--57},
publisher = {IEEE Symposium on Security and Privacy},
year = {2017}
}
@inproceedings{DBLP:conf/cvpr/Moosavi-Dezfooli16,
author = {Seyed-Mohsen Moosavi-Dezfooli and
Alhussein Fawzi and
Pascal Frossard},
title = {DeepFool: {A} Simple and Accurate Method to Fool Deep Neural Networks},
pages = {2574--2582},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2016}
}
@inproceedings{DBLP:conf/acl/ChengJM19,
author = {Yong Cheng and
Lu Jiang and
Wolfgang Macherey},
title = {Robust Neural Machine Translation with Doubly Adversarial Inputs},
pages = {4324--4333},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/cvpr/NguyenYC15,
author = {Anh Mai Nguyen and
Jason Yosinski and
Jeff Clune},
title = {Deep neural networks are easily fooled: High confidence predictions
for unrecognizable images},
pages = {427--436},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2015}
}
@inproceedings{DBLP:journals/corr/SzegedyZSBEGF13,
author = {Christian Szegedy and
Wojciech Zaremba and
Ilya Sutskever and
Joan Bruna and
Dumitru Erhan and
Ian J. Goodfellow and
Rob Fergus},
title = {Intriguing properties of neural networks},
publisher = {International Conference on Learning Representations},
year = {2014}
}
@inproceedings{DBLP:journals/corr/GoodfellowSS14,
author = {Ian J. Goodfellow and
Jonathon Shlens and
Christian Szegedy},
title = {Explaining and Harnessing Adversarial Examples},
publisher = {International Conference on Learning Representations},
year = {2015}
}
@inproceedings{DBLP:conf/emnlp/JiaL17,
author = {Robin Jia and
Percy Liang},
title = {Adversarial Examples for Evaluating Reading Comprehension Systems},
pages = {2021--2031},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/BekoulisDDD18,
author = {Giannis Bekoulis and
Johannes Deleu and
Thomas Demeester and
Chris Develder},
title = {Adversarial training for multi-context joint entity and relation extraction},
pages = {2830--2836},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/naacl/YasunagaKR18,
author = {Michihiro Yasunaga and
Jungo Kasai and
Dragomir R. Radev},
title = {Robust Multilingual Part-of-Speech Tagging via Adversarial Training},
pages = {976--986},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/iclr/BelinkovB18,
author = {Yonatan Belinkov and
Yonatan Bisk},
title = {Synthetic and Natural Noise Both Break Neural Machine Translation},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{DBLP:conf/naacl/MichelLNP19,
author = {Paul Michel and
Xian Li and
Graham Neubig and
Juan Miguel Pino},
title = {On Evaluation of Adversarial Perturbations for Sequence-to-Sequence
Models},
pages = {3103--3114},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{Gong2018AdversarialTW,
title={Adversarial Texts with Gradient Methods},
author={Zhitao Gong and Wenlu Wang and B. Li and D. Song and W. Ku},
publisher={ArXiv},
year={2018},
volume={abs/1801.07175}
}
@inproceedings{DBLP:conf/naacl/VaibhavSSN19,
author = {Vaibhav and
Sumeet Singh and
Craig Stewart and
Graham Neubig},
title = {Improving Robustness of Machine Translation with Synthetic Noise},
pages = {1916--1920},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/naacl/AnastasopoulosL19,
author = {Antonios Anastasopoulos and
Alison Lui and
Toan Q. Nguyen and
David Chiang},
title = {Neural Machine Translation of Text from Non-Native Speakers},
pages = {3070--3080},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/SinghGR18,
author = {Marco T{\'{u}}lio Ribeiro and
Sameer Singh and
Carlos Guestrin},
title = {Semantically Equivalent Adversarial Rules for Debugging {NLP} models},
pages = {856--865},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:journals/corr/SamantaM17,
author = {Suranjana Samanta and
Sameep Mehta},
title = {Towards Crafting Text Adversarial Samples},
publisher = {CoRR},
volume = {abs/1707.02812},
year = {2017}
}
@inproceedings{DBLP:conf/ijcai/0002LSBLS18,
author = {Bin Liang and
Hongcheng Li and
Miaoqiang Su and
Pan Bian and
Xirong Li and
Wenchang Shi},
title = {Deep Text Classification Can be Fooled},
pages = {4208--4215},
publisher = {International Joint Conference on Artificial Intelligence},
year = {2018}
}
@inproceedings{DBLP:conf/coling/EbrahimiLD18,
author = {Javid Ebrahimi and
Daniel Lowd and
Dejing Dou},
title = {On Adversarial Examples for Character-Level Neural Machine Translation},
pages = {653--663},
publisher = {International Conference on Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/iclr/ZhaoDS18,
author = {Zhengli Zhao and
Dheeru Dua and
Sameer Singh},
title = {Generating Natural Adversarial Examples},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{DBLP:conf/acl/LiuTMCZ18,
author = {Yong Cheng and
Zhaopeng Tu and
Fandong Meng and
Junjie Zhai and
Yang Liu},
title = {Towards Robust Neural Machine Translation},
pages = {1756--1766},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/acl/LiuMHXH19,
author = {Hairong Liu and
Mingbo Ma and
Liang Huang and
Hao Xiong and
Zhongjun He},
title = {Robust Neural Machine Translation with Joint Textual and Phonetic
Embedding},
pages = {3044--3049},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/LiLWJXZLL20,
author = {Bei Li and
Hui Liu and
Ziyang Wang and
Yufan Jiang and
Tong Xiao and
Jingbo Zhu and
Tongran Liu and
Changliang Li},
title = {Does Multi-Encoder Help? {A} Case Study on Context-Aware Neural Machine
Translation},
pages = {3512--3518},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@techreport{chen1999gaussian,
title={A Gaussian prior for smoothing maximum entropy models},
author={Chen, Stanley F and Rosenfeld, Ronald},
year={1999},
institution={CARNEGIE-MELLON UNIV PITTSBURGH PA SCHOOL OF COMPUTER SCIENCE}
}
@inproceedings{DBLP:conf/emnlp/MichelN18,
author = {Paul Michel and
Graham Neubig},
title = {{MTNT:} {A} Testbed for Machine Translation of Noisy Text},
pages = {543--553},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/icassp/SchusterN12,
author = {Mike Schuster and
Kaisuke Nakajima},
title = {Japanese and Korean voice search},
pages = {5149--5152},
publisher = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2012}
}
@inproceedings{kudo2018sentencepiece,
title={SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing},
author={Taku {Kudo} and John {Richardson}},
publisher={Conference on Empirical Methods in Natural Language Processing},
pages={66--71},
year={2018}
}
@inproceedings{provilkov2020bpe,
title={BPE-Dropout: Simple and Effective Subword Regularization},
author={Ivan {Provilkov} and Dmitrii {Emelianenko} and Elena {Voita}},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={1882--1892},
year={2020}
}
@inproceedings{he2020dynamic,
title={Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation},
author={Xuanli {He} and Gholamreza {Haffari} and Mohammad {Norouzi}},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={3042--3051},
year={2020}
}
@inproceedings{DBLP:journals/mt/EetemadiLTR15,
author = {Sauleh Eetemadi and
William Lewis and
Kristina Toutanova and
Hayder Radha},
title = {Survey of data-selection methods in statistical machine translation},
publisher = {Machine Translation},
volume = {29},
number = {3-4},
pages = {189--223},
year = {2015}
}
@inproceedings{britz2017effective,
title={Effective domain mixing for neural machine translation},
author={Britz, Denny and Le, Quoc and Pryzant, Reid},
publisher={Proceedings of the Second Conference on Machine Translation},
pages={118--126},
year={2017}
}
@inproceedings{DBLP:conf/emnlp/AxelrodHG11,
author = {Amittai Axelrod and
Xiaodong He and
Jianfeng Gao},
title = {Domain Adaptation via Pseudo In-Domain Data Selection},
pages = {355--362},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2011}
}
@inproceedings{DBLP:conf/wmt/AxelrodRHO15,
author = {Amittai Axelrod and
Philip Resnik and
Xiaodong He and
Mari Ostendorf},
title = {Data Selection With Fewer Words},
pages = {58--65},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2015}
}
@inproceedings{DBLP:conf/emnlp/WangULCS17,
author = {Rui Wang and
Masao Utiyama and
Lemao Liu and
Kehai Chen and
Eiichiro Sumita},
title = {Instance Weighting for Neural Machine Translation Domain Adaptation},
pages = {1482--1488},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/iwslt/MansourWN11,
author = {Saab Mansour and
Joern Wuebker and
Hermann Ney},
title = {Combining translation and language model scoring for domain-specific
data filtering},
pages = {222--229},
publisher = {International Workshop on Spoken Language Translation},
year = {2011}
}
@inproceedings{DBLP:conf/conll/ChenH16,
author = {Boxing Chen and
Fei Huang},
title = {Semi-supervised Convolutional Networks for Translation Adaptation
with Tiny Amount of In-domain Data},
pages = {314--323},
publisher = {The SIGNLL Conference on Computational Natural Language Learning},
year = {2016}
}
@inproceedings{chen2016bilingual,
title={Bilingual methods for adaptive training data selection for machine translation},
author={Chen, Boxing and Kuhn, Roland and Foster, George and Cherry, Colin and Huang, Fei},
publisher={Association for Machine Translation in the Americas},
pages={93--103},
year={2016}
}
@inproceedings{DBLP:conf/aclnmt/ChenCFL17,
author = {Boxing Chen and
Colin Cherry and
George F. Foster and
Samuel Larkin},
title = {Cost Weighting for Neural Machine Translation Domain Adaptation},
pages = {40--46},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/wmt/DumaM17,
author = {Mirela-Stefania Duma and
Wolfgang Menzel},
title = {Automatic Threshold Detection for Data Selection in Machine Translation},
pages = {483--488},
publisher = {Proceedings of the Second Conference on Machine Translation},
year = {2017}
}
@inproceedings{DBLP:conf/wmt/BiciciY11,
author = {Ergun Bi{\c{c}}ici and
Deniz Yuret},
title = {Instance Selection for Machine Translation using Feature Decay Algorithms},
pages = {272--283},
publisher = {Proceedings of the Sixth Workshop on Statistical Machine Translation},
year = {2011}
}
@inproceedings{poncelas2018feature,
title={Feature decay algorithms for neural machine translation},
author={Poncelas, Alberto and Maillette de Buy Wenniger, Gideon and Way, Andy},
year={2018},
publisher={European Association for Machine Translation}
}
@inproceedings{DBLP:conf/acl/SotoSPW20,
author = {Xabier Soto and
Dimitar Sht. Shterionov and
Alberto Poncelas and
Andy Way},
title = {Selecting Backtranslated Data from Multiple Sources for Improved Neural
Machine Translation},
pages = {3898--3908},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-1811-03039,
author = {Alberto Poncelas and
Gideon Maillette de Buy Wenniger and
Andy Way},
title = {Data Selection with Feature Decay Algorithms Using an Approximated
Target Side},
publisher = {CoRR},
volume = {abs/1811.03039},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/WeesBM17,
author = {Marlies van der Wees and
Arianna Bisazza and
Christof Monz},
title = {Dynamic Data Selection for Neural Machine Translation},
pages = {1400--1410},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/wmt/WangWHNC18,
author = {Wei Wang and
Taro Watanabe and
Macduff Hughes and
Tetsuji Nakagawa and
Ciprian Chelba},
title = {Denoising Neural Machine Translation Training with Trusted Data and
Online Data Selection},
pages = {133--143},
publisher = {Proceedings of the Third Conference on Machine Translation},
year = {2018}
}
@inproceedings{DBLP:conf/acl/WangUS18,
author = {Rui Wang and
Masao Utiyama and
Eiichiro Sumita},
title = {Dynamic Sentence Sampling for Efficient Training of Neural Machine
Translation},
pages = {298--304},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/aclnmt/KhayrallahK18,
author = {Huda Khayrallah and
Philipp Koehn},
title = {On the Impact of Various Types of Noise on Neural Machine Translation},
pages = {74--83},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/coling/FormigaF12,
author = {Llu{\'{\i}}s Formiga and
Jos{\'{e}} A. R. Fonollosa},
title = {Dealing with Input Noise in Statistical Machine Translation},
pages = {319--328},
publisher = {International Conference on Computational Linguistics},
year = {2012}
}
@inproceedings{DBLP:conf/acl/CuiZLLZ13,
author = {Lei Cui and
Dongdong Zhang and
Shujie Liu and
Mu Li and
Ming Zhou},
title = {Bilingual Data Cleaning for {SMT} using Graph-based Random Walk},
pages = {340--345},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@phdthesis{DBLP:phd/dnb/Mediani17,
author = {Mohammed Mediani},
title = {Learning from Noisy Data in Statistical Machine Translation},
school = {Karlsruhe Institute of Technology, Germany},
year = {2017}
}
@inproceedings{rarrick2011mt,
title={MT detection in web-scraped parallel corpora},
author={Rarrick, Spencer and Quirk, Chris and Lewis, Will},
publisher={Machine Translation},
pages={422--430},
year={2011}
}
@inproceedings{taghipour2011parallel,
title={Parallel corpus refinement as an outlier detection algorithm},
author={Taghipour, Kaveh and Khadivi, Shahram and Xu, Jia},
publisher={Machine Translation},
pages={414--421},
year={2011}
}
@inproceedings{Xu2017ZipporahAF,
title={Zipporah: a Fast and Scalable Data Cleaning System for Noisy Web-Crawled Parallel Corpora},
author={Hainan Xu and Philipp Koehn},
booktitle={Conference on Empirical Methods in Natural Language Processing},
year={2017}
}
@inproceedings{DBLP:conf/aclnmt/CarpuatVN17,
author = {Marine Carpuat and
Yogarshi Vyas and
Xing Niu},
title = {Detecting Cross-Lingual Semantic Divergence for Neural Machine Translation},
pages = {69--79},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/naacl/VyasNC18,
author = {Yogarshi Vyas and
Xing Niu and
Marine Carpuat},
title = {Identifying Semantic Divergences in Parallel Text without Annotations},
pages = {1503--1515},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/acl/WangCC19,
author = {Wei Wang and
Isaac Caswell and
Ciprian Chelba},
title = {Dynamically Composing Domain-Data Selection with Clean-Data Selection
by "Co-Curricular Learning" for Neural Machine Translation},
pages = {1282--1292},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/SettlesC08,
author = {Burr Settles and
Mark Craven},
title = {An Analysis of Active Learning Strategies for Sequence Labeling Tasks},
pages = {1070--1079},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2008}
}
@inproceedings{campbell2000query,
title={Query learning with large margin classifiers},
author={Campbell, Colin and Cristianini, Nello and Smola, Alex and others},
publisher={International Conference on Machine Learning},
volume={20},
number={0},
pages={0},
year={2000}
}
@inproceedings{DBLP:conf/icml/SchohnC00,
author = {Greg Schohn and
David Cohn},
title = {Less is More: Active Learning with Support Vector Machines},
pages = {839--846},
publisher = {International Conference on Machine Learning},
year = {2000}
}
@inproceedings{DBLP:conf/colt/SeungOS92,
author = {H. Sebastian Seung and
Manfred Opper and
Haim Sompolinsky},
title = {Query by Committee},
pages = {287--294},
publisher = {Conference on Computational Learning Theory},
year = {1992}
}
@book{mitchell1996m,
title={Machine Learning},
author={Mitchell, Tom},
journal={McCraw Hill},
year={1996}
}
@inproceedings{DBLP:conf/icml/AbeM98,
author = {Naoki Abe and
Hiroshi Mamitsuka},
title = {Query Learning Strategies Using Boosting and Bagging},
pages = {1--9},
publisher = {International Conference on Machine Learning},
year = {1998}
}
@inproceedings{mccallumzy1998employing,
title={Employing EM and pool-based active learning for text classification},
author={McCallumzy, Andrew Kachites and Nigamy, Kamal},
publisher={International Conference on Machine Learning},
pages={359--367},
year={1998}
}
@inproceedings{DBLP:conf/cvpr/DalalT05,
author = {Navneet Dalal and
Bill Triggs},
title = {Histograms of Oriented Gradients for Human Detection},
pages = {886--893},
publisher = {{IEEE} Conference on Computer Vision and Pattern Recognition},
year = {2005}
}
@inproceedings{726791,
author={Yann {Lecun} and Leon {Bottou} and Yoshua {Bengio} and Patrick {Haffner}},
publisher={Proceedings of the IEEE},
title={Gradient-based learning applied to document recognition},
year={1998},
volume={86},
number={11},
pages={2278-2324}
}
@book{atkinson2007optimum,
title={Optimum experimental designs, with SAS},
author={Atkinson, Anthony and Donev, Alexander and Tobias, Randall and others},
volume={34},
year={2007},
publisher={Oxford University Press}
}
@inproceedings{DBLP:journals/jmlr/JiH12,
author = {Ming Ji and
Jiawei Han},
title = {A Variance Minimization Criterion to Active Learning on Graphs},
series = {{JMLR} Proceedings},
volume = {22},
pages = {556--564},
publisher = {International Conference on Artificial Intelligence and Statistics},
year = {2012}
}
@inproceedings{DBLP:journals/corr/ZhuB17,
author = {Jia-Jie Zhu and
Jos{\'{e}} Bento},
title = {Generative Adversarial Active Learning},
publisher = {CoRR},
volume = {abs/1702.07956},
year = {2017}
}
@inproceedings{DBLP:conf/iccv/HuijserG17,
author = {Miriam W. Huijser and
Jan C. van Gemert},
title = {Active Decision Boundary Annotation with Deep Generative Models},
pages = {5296--5305},
publisher = {{IEEE} International Conference on Computer Vision},
year = {2017}
}
@inproceedings{DBLP:conf/wacv/0007T20,
author = {Christoph Mayer and
Radu Timofte},
title = {Adversarial Sampling for Active Learning},
pages = {3060--3068},
publisher = {{IEEE} Winter Conference on Applications of Computer Vision},
year = {2020}
}
@inproceedings{DBLP:conf/acl/JeanCMB15,
author = {S{\'{e}}bastien Jean and
KyungHyun Cho and
Roland Memisevic and
Yoshua Bengio},
title = {On Using Very Large Target Vocabulary for Neural Machine Translation},
pages = {1--10},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{2015OnGulcehre,
title = {On Using Monolingual Corpora in Neural Machine Translation},
author = {Gulcehre Caglar and
Firat Orhan and
Xu Kelvin and
Cho Kyunghyun and
Barrault Loic and
Lin Huei Chi and
Bougares Fethi and
Schwenk Holger and
Bengio Yoshua},
publisher = {Computer Science},
year = {2015},
}
@inproceedings{Sennrich2016ImprovingNM,
author = {Rico Sennrich and
Barry Haddow and
Alexandra Birch},
title = {Improving Neural Machine Translation Models with Monolingual Data},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/aaai/Zhang0LZC18,
author = {Zhirui Zhang and
Shujie Liu and
Mu Li and
Ming Zhou and
Enhong Chen},
title = {Joint Training for Neural Machine Translation Models with Monolingual
Data},
pages = {555--562},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2018}
}
@inproceedings{hoang2018iterative,
title={Iterative back-translation for neural machine translation},
author={Hoang, Vu Cong Duy and Koehn, Philipp and Haffari, Gholamreza and Cohn, Trevor},
publisher={Proceedings of the 2nd Workshop on Neural Machine Translation and Generation},
pages={18--24},
year={2018}
}
@inproceedings{DBLP:conf/mtsummit/ImankulovaDFI19,
author = {Aizhan Imankulova and
Raj Dabre and
Atsushi Fujita and
Kenji Imamura},
title = {Exploiting Out-of-Domain Parallel Data through Multilingual Transfer
Learning for Low-Resource Neural Machine Translation},
pages = {128--139},
publisher = {Machine Translation},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/CurreyH19,
author = {Anna Currey and
Kenneth Heafield},
title = {Zero-Resource Neural Machine Translation with Monolingual Pivot Data},
pages = {99--107},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/KimPPKN19,
author = {Yunsu Kim and
Petre Petrov and
Pavel Petrushkov and
Shahram Khadivi and
Hermann Ney},
title = {Pivot-based Transfer Learning for Neural Machine Translation between
Non-English Languages},
pages = {866--876},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/iclr/LampleCDR18,
author = {Guillaume Lample and
Alexis Conneau and
Ludovic Denoyer and
Marc'Aurelio Ranzato},
title = {Unsupervised Machine Translation Using Monolingual Corpora Only},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{DBLP:conf/iclr/ArtetxeLAC18,
author = {Mikel Artetxe and
Gorka Labaka and
Eneko Agirre and
Kyunghyun Cho},
title = {Unsupervised Neural Machine Translation},
publisher = {International Conference on Learning Representations},
year = {2018}
}
%下面的publisher在看看
@inproceedings{DBLP:conf/conll/LiuBH18,
author = {Ming Liu and
Wray L. Buntine and
Gholamreza Haffari},
title = {Learning to Actively Learn Neural Machine Translation},
pages = {334--344},
publisher = {The SIGNLL Conference on Computational Natural Language Learning},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/ZhaoZZZ20,
author = {Yuekai Zhao and
Haoran Zhang and
Shuchang Zhou and
Zhihua Zhang},
title = {Active Learning Approaches to Enhancing Neural Machine Translation:
An Empirical Study},
pages = {1796--1806},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2020}
}
@inproceedings{Peris2018ActiveLF,
title={Active Learning for Interactive Neural Machine Translation of Data Streams},
author={{\'A}lvaro Peris and Francisco Casacuberta},
publisher={The SIGNLL Conference on Computational Natural Language Learning},
pages={151--160},
year={2018}
}
@inproceedings{DBLP:journals/pbml/TurchiNFF17,
author = {Marco Turchi and
Matteo Negri and
M. Amin Farajian and
Marcello Federico},
title = {Continuous Learning from Human Post-Edits for Neural Machine Translation},
publisher = {The Prague Bulletin of Mathematical Linguistics},
volume = {108},
pages = {233--244},
year = {2017}
}
@inproceedings{DBLP:journals/csl/PerisC19,
author = {{\'{A}}lvaro Peris and
Francisco Casacuberta},
title = {Online learning for effort reduction in interactive neural machine
translation},
publisher = {Computer Speech Language},
volume = {58},
pages = {98--126},
year = {2019}
}
@inproceedings{DBLP:conf/eccv/GuoHZZDSH18,
author = {Sheng Guo and
Weilin Huang and
Haozhi Zhang and
Chenfan Zhuang and
Dengke Dong and
Matthew R. Scott and
Dinglong Huang},
title = {CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images},
series = {Lecture Notes in Computer Science},
volume = {11214},
pages = {139--154},
publisher = {European Conference on Computer Vision},
year = {2018}
}
@inproceedings{DBLP:conf/mm/JiangMMH14,
author = {Lu Jiang and
Deyu Meng and
Teruko Mitamura and
Alexander G. Hauptmann},
title = {Easy Samples First: Self-paced Reranking for Zero-Example Multimedia
Search},
pages = {547--556},
publisher = {ACM International Conference on Multimedia},
year = {2014}
}
%下面的pubisher
@inproceedings{DBLP:conf/naacl/PlataniosSNPM19,
author = {Emmanouil Antonios Platanios and
Otilia Stretcu and
Graham Neubig and
Barnab{\'{a}}s P{\'{o}}czos and
Tom M. Mitchell},
title = {Competence-based Curriculum Learning for Neural Machine Translation},
pages = {1162--1172},
publisher = {Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
year = {2019}
}
@inproceedings{DBLP:conf/acl/TayWLFPYRHZ19,
author = {Yi Tay and
Shuohang Wang and
Anh Tuan Luu and
Jie Fu and
Minh C. Phan and
Xingdi Yuan and
Jinfeng Rao and
Siu Cheung Hui and
Aston Zhang},
title = {Simple and Effective Curriculum Pointer-Generator Networks for Reading
Comprehension over Long Narratives},
pages = {4922--4931},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/icml/GuoCZZ0HT20,
author = {Yong Guo and
Yaofo Chen and
Yin Zheng and
Peilin Zhao and
Jian Chen and
Junzhou Huang and
Mingkui Tan},
title = {Breaking the Curse of Space Explosion: Towards Efficient {NAS} with
Curriculum Search},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {3822--3831},
publisher = {International Conference on Machine Learning},
year = {2020}
}
@inproceedings{DBLP:conf/ranlp/KocmiB17,
author = {Tom Kocmi and
Ondrej Bojar},
title = {Curriculum Learning and Minibatch Bucketing in Neural Machine Translation},
pages = {379--386},
publisher = {International Conference Recent Advances in Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/naacl/ZhangSKMCD19,
author = {Xuan Zhang and
Pamela Shapiro and
Gaurav Kumar and
Paul McNamee and
Marine Carpuat and
Kevin Duh},
title = {Curriculum Learning for Domain Adaptation in Neural Machine Translation},
pages = {1903--1915},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{zhang2018empirical,
title={An empirical exploration of curriculum learning for neural machine translation},
author={Zhang, Xuan and Kumar, Gaurav and Khayrallah, Huda and Murray, Kenton and Gwinnup, Jeremy and Martindale, Marianna J and McNamee, Paul and Duh, Kevin and Carpuat, Marine},
publisher={arXiv preprint arXiv:1811.00739},
year={2018}
}
@inproceedings{DBLP:conf/coling/XuHJFWHJXZ20,
author = {Chen Xu and
Bojie Hu and
Yufan Jiang and
Kai Feng and
Zeyang Wang and
Shen Huang and
Qi Ju and
Tong Xiao and
Jingbo Zhu},
title = {Dynamic Curriculum Learning for Low-Resource Neural Machine Translation},
pages = {3977--3989},
publisher = {International Committee on Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/acl/ZhouYWWC20,
author = {Yikai Zhou and
Baosong Yang and
Derek F. Wong and
Yu Wan and
Lidia S. Chao},
title = {Uncertainty-Aware Curriculum Learning for Neural Machine Translation},
pages = {6934--6944},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/aaai/ZhaoWNW20,
author = {Mingjun Zhao and
Haijiang Wu and
Di Niu and
Xiaoli Wang},
title = {Reinforced Curriculum Learning on Pre-Trained Neural Machine Translation
Models},
pages = {9652--9659},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2020}
}
@inproceedings{DBLP:conf/cvpr/PentinaSL15,
author = {Anastasia Pentina and
Viktoriia Sharmanska and
Christoph H. Lampert},
title = {Curriculum learning of multiple tasks},
pages = {5492--5500},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2015}
}
@inproceedings{DBLP:conf/iccvw/SarafianosGNK17,
author = {Nikolaos Sarafianos and
Theodore Giannakopoulos and
Christophoros Nikou and
Ioannis A. Kakadiaris},
title = {Curriculum Learning for Multi-task Classification of Visual Attributes},
pages = {2608--2615},
publisher = {IEEE International Conference on Computer Vision},
year = {2017}
}
@inproceedings{DBLP:conf/nips/ChangLM17,
author = {Haw-Shiuan Chang and
Erik G. Learned-Miller and
Andrew McCallum},
title = {Active Bias: Training More Accurate Neural Networks by Emphasizing
High Variance Samples},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {1002--1012},
year = {2017}
}
%ieee加{
@inproceedings{DBLP:journals/pami/LiH18a,
author = {Zhizhong Li and
Derek Hoiem},
title = {Learning without Forgetting},
publisher = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume = {40},
number = {12},
pages = {2935--2947},
year = {2018}
}
@inproceedings{rusu2016progressive,
title={Progressive neural networks},
author={Rusu, Andrei A and Rabinowitz, Neil C and Desjardins, Guillaume and Soyer, Hubert and Kirkpatrick, James and Kavukcuoglu, Koray and Pascanu, Razvan and Hadsell, Raia},
publisher={arXiv preprint arXiv:1606.04671},
year={2016}
}
@inproceedings{DBLP:journals/corr/FernandoBBZHRPW17,
author = {Chrisantha Fernando and
Dylan Banarse and
Charles Blundell and
Yori Zwols and
David Ha and
Andrei A. Rusu and
Alexander Pritzel and
Daan Wierstra},
title = {PathNet: Evolution Channels Gradient Descent in Super Neural Networks},
publisher = {CoRR},
volume = {abs/1701.08734},
year = {2017}
}
@inproceedings{DBLP:conf/naacl/ThompsonGKDK19,
author = {Brian Thompson and
Jeremy Gwinnup and
Huda Khayrallah and
Kevin Duh and
Philipp Koehn},
title = {Overcoming Catastrophic Forgetting During Domain Adaptation of Neural
Machine Translation},
pages = {2062--2068},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/coling/GuF20,
author = {Shuhao Gu and
Yang Feng},
title = {Investigating Catastrophic Forgetting During Continual Training for
Neural Machine Translation},
pages = {4315--4326},
publisher = {International Committee on Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/cvpr/RebuffiKSL17,
author = {Sylvestre-Alvise Rebuffi and
Alexander Kolesnikov and
Georg Sperl and
Christoph H. Lampert},
title = {iCaRL: Incremental Classifier and Representation Learning},
pages = {5533--5542},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2017}
}
@inproceedings{DBLP:conf/eccv/CastroMGSA18,
author = {Francisco M. Castro and
Manuel J. Mar{\'{\i}}n-Jim{\'{e}}nez and
Nicol{\'{a}}s Guil and
Cordelia Schmid and
Karteek Alahari},
title = {End-to-End Incremental Learning},
series = {Lecture Notes in Computer Science},
volume = {11216},
pages = {241--257},
publisher = {European Conference on Computer Vision},
year = {2018}
}
@inproceedings{Bengio2015ScheduledSF,
title={Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks},
author={Samy Bengio and
Oriol Vinyals and
Navdeep Jaitly and
Noam Shazeer},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {1171--1179},
year = {2015}
}
@inproceedings{Bengio2015ScheduledSF,
title={Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks},
author={Samy Bengio and
Oriol Vinyals and
Navdeep Jaitly and
Noam Shazeer},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {1171--1179},
year = {2015}
}
@inproceedings{Ranzato2016SequenceLT,
title={Sequence Level Training with Recurrent Neural Networks},
author={Marc'Aurelio Ranzato and
Sumit Chopra and
Michael Auli and
Wojciech Zaremba},
publisher={International Conference on Learning Representations},
year={2016}
}
@inproceedings{DBLP:conf/nips/GoodfellowPMXWOCB14,
author = {Ian J. Goodfellow and
Jean Pouget-Abadie and
Mehdi Mirza and
Bing Xu and
David Warde-Farley and
Sherjil Ozair and
Aaron C. Courville and
Yoshua Bengio},
title = {Generative Adversarial Nets},
publisher = {Conference on Neural Information Processing Systems},
pages = {2672--2680},
year = {2014}
}
@inproceedings{DBLP:conf/acl/ShenCHHWSL16,
author = {Shiqi Shen and
Yong Cheng and
Zhongjun He and
Wei He and
Hua Wu and
Maosong Sun and
Yang Liu},
title = {Minimum Risk Training for Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016},
}
@inproceedings{DBLP:conf/acl/PapineniRWZ02,
author = {Kishore Papineni and
Salim Roukos and
Todd Ward and
Wei-jing Zhu},
title = {Bleu: a Method for Automatic Evaluation of Machine Translation},
pages = {311--318},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2002}
}
@inproceedings{doddington2002automatic,
title={Automatic evaluation of machine translation quality using n-gram co-occurrence statistics},
publisher={Proceedings of the second international conference on Human Language Technology Research},
author={Doddington, George},
pages={138--145},
year={2002}
}
@inproceedings{snover2006study,
title={A study of translation edit rate with targeted human annotation},
author={Snover, Matthew and Dorr, Bonnie and Schwartz, Richard and Micciulla, Linnea and Makhoul, John},
publisher={Proceedings of association for machine translation in the Americas},
volume={200},
number={6},
year={2006}
}
@inproceedings{lavie2009meteor,
title={The METEOR metric for automatic evaluation of machine translation},
author={Lavie, Alon and Denkowski, Michael J},
publisher={Machine translation},
volume={23},
number={2-3},
pages={105--115},
year={2009}
}
@inproceedings{bahdanau2014neural,
author = {Dzmitry Bahdanau and
Kyunghyun Cho and
Yoshua Bengio},
title = {Neural Machine Translation by Jointly Learning to Align and Translate},
publisher = {International Conference on Learning Representations},
year = {2015}
}
@inproceedings{koehn2003statistical,
author = {Philipp Koehn and
Franz Josef Och and
Daniel Marcu},
title = {Statistical Phrase-Based Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2003}
}
@inproceedings{smith2006minimum,
author = {David A. Smith and
Jason Eisner},
title = {Minimum Risk Annealing for Training Log-Linear Models},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2006}
}
@inproceedings{he2012maximum,
title={Maximum expected bleu training of phrase and lexicon translation models},
author={He, Xiaodong and Deng, Li},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={292--301},
year={2012}
}
@inproceedings{DBLP:conf/acl/GaoHYD14,
author = {Jianfeng Gao and
Xiaodong He and
Wen-tau Yih and
Li Deng},
title = {Learning Continuous Phrase Representations for Translation Modeling},
pages = {699--709},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@book{sutton2018reinforcement,
title={Reinforcement learning: An introduction},
author={Richard S. Sutton and Andrew G. Barto},
year={2018},
publisher={MIT press}
}
@inproceedings{DBLP:journals/nature/SilverHMGSDSAPL16,
author = {David Silver and
Aja Huang and
Chris J. Maddison and
Arthur Guez and
Laurent Sifre and
George van den Driessche and
Julian Schrittwieser and
Ioannis Antonoglou and
Vedavyas Panneershelvam and
Marc Lanctot and
Sander Dieleman and
Dominik Grewe and
John Nham and
Nal Kalchbrenner and
Ilya Sutskever and
Timothy P. Lillicrap and
Madeleine Leach and
Koray Kavukcuoglu and
Thore Graepel and
Demis Hassabis},
title = {Mastering the game of Go with deep neural networks and tree search},
publisher = {Nature},
volume = {529},
number = {7587},
pages = {484--489},
year = {2016}
}
@inproceedings{DBLP:conf/icml/ZarembaMJF16,
author = {Wojciech Zaremba and
Tomas Mikolov and
Armand Joulin and
Rob Fergus},
title = {Learning Simple Algorithms from Examples},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {48},
pages = {421--429},
publisher = {International Conference on Machine Learning},
year = {2016}
}
@inproceedings{DBLP:conf/icml/NgHR99,
author = {Andrew Y. Ng and
Daishi Harada and
Stuart J. Russell},
title = {Policy Invariance Under Reward Transformations: Theory and Application
to Reward Shaping},
pages = {278--287},
publisher = {International Conference on Machine Learning},
year = {1999}
}
@inproceedings{DBLP:conf/iclr/BahdanauBXGLPCB17,
author = {Dzmitry Bahdanau and
Philemon Brakel and
Kelvin Xu and
Anirudh Goyal and
Ryan Lowe and
Joelle Pineau and
Aaron C. Courville and
Yoshua Bengio},
title = {An Actor-Critic Algorithm for Sequence Prediction},
publisher = {International Conference on Learning Representations},
year = {2017}
}
@inproceedings{DBLP:journals/nature/LeCunBH15,
author = {Yann LeCun and
Yoshua Bengio and
Geoffrey E. Hinton},
title = {Deep learning},
publisher = {Nature},
volume = {521},
number = {7553},
pages = {436--444},
year = {2015}
}
@inproceedings{DBLP:journals/corr/abs-1207-0580,
author = {Geoffrey E. Hinton and
Nitish Srivastava and
Alex Krizhevsky and
Ilya Sutskever and
Ruslan Salakhutdinov},
title = {Improving neural networks by preventing co-adaptation of feature detectors},
publisher = {CoRR},
volume = {abs/1207.0580},
year = {2012}
}
@inproceedings{DBLP:journals/tslp/ZhuM12,
author = {Jingbo Zhu and
Matthew Y. Ma},
title = {Uncertainty-based active learning with instability estimation for
text classification},
publisher = {ACM Transactions on Speech and Language Processing},
volume = {8},
number = {4},
pages = {5:1--5:21},
year = {2012}
}
@inproceedings{DBLP:conf/coling/ZhuWYT08,
author = {Jingbo Zhu and
Huizhen Wang and
Tianshun Yao and
Benjamin K. Tsou},
title = {Active Learning with Sampling by Uncertainty and Density for Word
Sense Disambiguation and Text Classification},
publisher = {International Conference on Computational Linguistics},
pages = {1137--1144},
year = {2008}
}
@inproceedings{DBLP:conf/medprai/SurendranathJ18,
author = {Ajay Surendranath and
Dinesh Babu Jayagopi},
title = {Curriculum Learning for Depth Estimation with Deep Convolutional Neural
Networks},
publisher = {Mediterranean Conference on Pattern Recognition and Artificial Intelligence},
pages = {95--100},
year = {2018}
}
@inproceedings{DBLP:conf/icml/BengioLCW09,
author = {Yoshua Bengio and
J{\'{e}}r{\^{o}}me Louradour and
Ronan Collobert and
Jason Weston},
title = {Curriculum learning},
series = {{ACM} International Conference Proceeding Series},
volume = {382},
pages = {41--48},
publisher = {International Conference on Machine Learning}
}
@inproceedings{DBLP:journals/corr/abs-2002-11794,
author = {Zhuohan Li and
Eric Wallace and
Sheng Shen and
Kevin Lin and
Kurt Keutzer and
Dan Klein and
Joseph E. Gonzalez},
title = {Train Large, Then Compress: Rethinking Model Size for Efficient Training
and Inference of Transformers},
publisher = {CoRR},
volume = {abs/2002.11794},
year = {2020}
}
@inproceedings{kim-rush-2016-sequence,
author = {Yoon Kim and
Alexander M. Rush},
title = {Sequence-Level Knowledge Distillation},
pages = {1317--1327},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2016}
}
@inproceedings{Jiao2020TinyBERTDB,
author = {Xiaoqi Jiao and
Yichun Yin and
Lifeng Shang and
Xin Jiang and
Xiao Chen and
Linlin Li and
Fang Wang and
Qun Liu},
title = {TinyBERT: Distilling {BERT} for Natural Language Understanding},
pages = {4163--4174},
publisher={Conference on Empirical Methods in Natural Language Processing},
year={2020}
}
%%%%% chapter 13------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 14------------------------------------------------------
@inproceedings{Koehn2007Moses,
author = {Philipp Koehn and
Hieu Hoang and
Alexandra Birch and
Chris Callison-Burch and
Marcello Federico and
Nicola Bertoldi and
Brooke Cowan and
Wade Shen and
Christine Moran and
Richard Zens and
Chris Dyer and
Ondrej Bojar and
Alexandra Constantin and
Evan Herbst},
title = {Moses: Open Source Toolkit for Statistical Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/amta/Koehn04,
author = {Philipp Koehn},
title = {Pharaoh: {A} Beam Search Decoder for Phrase-Based Statistical Machine
Translation Models},
volume = {3265},
pages = {115--124},
publisher = { Association for Machine Translation in the Americas},
year = {2004}
}
@inproceedings{DBLP:conf/emnlp/StahlbergHSB17,
author = {Felix Stahlberg and
Eva Hasler and
Danielle Saunders and
Bill Byrne},
title = {SGNMT - A Flexible NMT Decoding Platform for Quick Prototyping
of New Models and Search Strategies},
pages = {25--30},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2017}
}
@inproceedings{Liu2016AgreementOT,
title={Agreement on Target-bidirectional Neural Machine Translation},
author={Lemao Liu and
Masao Utiyama and
Andrew M. Finch and
Eiichiro Sumita},
pages = {411--416},
publisher = { Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/wmt/LiLXLLLWZXWFCLL19,
author = {Bei Li and
Yinqiao Li and
Chen Xu and
Ye Lin and
Jiqiang Liu and
Hui Liu and
Ziyang Wang and
Yuhao Zhang and
Nuo Xu and
Zeyang Wang and
Kai Feng and
Hexuan Chen and
Tengbo Liu and
Yanyang Li and
Qiang Wang and
Tong Xiao and
Jingbo Zhu},
title = {The NiuTrans Machine Translation Systems for {WMT19}},
pages = {257--266},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/wmt/SennrichHB16,
author = {Rico Sennrich and
Barry Haddow and
Alexandra Birch},
title = {Edinburgh Neural Machine Translation Systems for {WMT} 16},
pages = {371--376},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{Stahlberg2018TheUO,
title={The University of Cambridge's Machine Translation Systems for WMT18},
author={Felix Stahlberg and
Adri{\`{a}} de Gispert and
Bill Byrne},
pages = {504--512},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/aaai/ZhangSQLJW18,
author = {Xiangwen Zhang and
Jinsong Su and
Yue Qin and
Yang Liu and
Rongrong Ji and
Hongji Wang},
title = {Asynchronous Bidirectional Decoding for Neural Machine Translation},
pages = {5698--5705},
publisher = { AAAI Conference on Artificial Intelligence},
year = {2018}
}
@inproceedings{Li2017EnhancedNM,
title={Enhanced neural machine translation by learning from draft},
author={Aodong Li and
Shiyue Zhang and
Dong Wang and
Thomas Fang Zheng},
publisher={IEEE Asia-Pacific Services Computing Conference},
year={2017},
pages={1583-1587}
}
@inproceedings{ElMaghraby2018EnhancingTF,
title={Enhancing Translation from English to Arabic Using Two-Phase Decoder Translation},
author={Ayah ElMaghraby and Ahmed Rafea},
pages = {539--549},
publisher = {Intelligent Systems and Applications},
year = {2018}
}
@inproceedings{Geng2018AdaptiveMD,
title={Adaptive Multi-pass Decoder for Neural Machine Translation},
author={Xinwei Geng and
Xiaocheng Feng and
Bing Qin and
Ting Liu},
publisher ={Conference on Empirical Methods in Natural Language Processing},
pages={523--532},
year={2018}
}
@inproceedings{Lee2018DeterministicNN,
title={Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement},
author={Jason Lee and Elman Mansimov and Kyunghyun Cho},
pages = {1173--1182},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{Gu2019LevenshteinT,
title={Levenshtein Transformer},
author={Jiatao Gu and Changhan Wang and Jake Zhao},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {11179--11189},
year = {2019},
}
@inproceedings{Guo2020JointlyMS,
title={Jointly Masked Sequence-to-Sequence Model for Non-Autoregressive Neural Machine Translation},
author={Junliang Guo and Linli Xu and Enhong Chen},
pages = {376--385},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{Stahlberg2018AnOS,
title={An Operation Sequence Model for Explainable Neural Machine Translation},
author={Felix Stahlberg and Danielle Saunders and Bill Byrne},
pages = {175--186},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{Stern2019InsertionTF,
title={Insertion Transformer: Flexible Sequence Generation via Insertion Operations},
author={Mitchell Stern and William Chan and Jamie Kiros and Jakob Uszkoreit},
publisher={International Conference on Machine Learning},
pages={5976--5985},
year={2019}
}
@inproceedings{stling2017NeuralMT,
title={Neural machine translation for low-resource languages},
author={Robert {\"O}stling and J{\"{o}}rg Tiedemann},
publisher={CoRR},
year={2017},
volume={abs/1708.05729}
}
@inproceedings{Kikuchi2016ControllingOL,
title={Controlling Output Length in Neural Encoder-Decoders},
author={Yuta Kikuchi and
Graham Neubig and
Ryohei Sasano and
Hiroya Takamura and
Manabu Okumura},
pages = {1328--1338},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2016}
}
@inproceedings{Takase2019PositionalET,
title={Positional Encoding to Control Output Sequence Length},
author={Sho Takase and
Naoaki Okazaki},
publisher={Annual Conference of the North American Chapter of the Association for Computational Linguistics},
pages={3999--4004},
year={2019}
}
@inproceedings{Murray2018CorrectingLB,
title={Correcting Length Bias in Neural Machine Translation},
author={Kenton Murray and David Chiang},
pages = {212--223},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{Sountsov2016LengthBI,
title={Length bias in Encoder Decoder Models and a Case for Global Conditioning},
author={Pavel Sountsov and Sunita Sarawagi},
pages = {1516--1525},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2016}
}
@inproceedings{Jean2015MontrealNM,
title={Montreal Neural Machine Translation Systems for WMT'15},
author={S{\'{e}}bastien Jean and
Orhan Firat and
Kyunghyun Cho and
Roland Memisevic and
Yoshua Bengio},
publisher={Conference on Empirical Methods in Natural Language Processing},
pages={134--140},
year={2015}
}
@inproceedings{Yang2018OtemUtemOA,
title={Otem{\&}Utem: Over- and Under-Translation Evaluation Metric for NMT},
author={Jing Yang and
Biao Zhang and
Yue Qin and
Xiangwen Zhang and
Qian Lin and
Jinsong Su},
publisher={CCF International Conference on Natural Language Processing and Chinese Computing},
pages={291--302},
year={2018}
}
@inproceedings{Mi2016CoverageEM,
title={Coverage Embedding Models for Neural Machine Translation},
author={Haitao Mi and
Baskaran Sankaran and
Zhiguo Wang and
Abe Ittycheriah},
pages = {955--960},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2016}
}
@inproceedings{DBLP:conf/emnlp/HuangZM17,
author = {Liang Huang and
Kai Zhao and
Mingbo Ma},
title = {When to Finish? Optimal Beam Search for Neural Text Generation (modulo
beam size)},
pages = {2134--2139},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{Wiseman2016SequencetoSequenceLA,
title={Sequence-to-Sequence Learning as Beam-Search Optimization},
author={Sam Wiseman and Alexander M. Rush},
publisher={Conference on Empirical Methods in Natural Language Processing},
pages={1296--1306},
year={2016}
}
@inproceedings{DBLP:conf/emnlp/Yang0M18,
author = {Yilin Yang and
Liang Huang and
Mingbo Ma},
title = {Breaking the Beam Search Curse: {A} Study of (Re-)Scoring Methods
and Stopping Criteria for Neural Machine Translation},
pages = {3054--3059},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{Ma2019LearningTS,
title={Learning to Stop in Structured Prediction for Neural Machine Translation},
author={Mingbo Ma and
Renjie Zheng and
Liang Huang},
pages = {1884--1889},
publisher = { Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{KleinOpenNMT,
author = {Guillaume Klein and
Yoon Kim and
Yuntian Deng and
Jean Senellart and
Alexander M. Rush},
title = {OpenNMT: Open-Source Toolkit for Neural Machine Translation},
pages = {67--72},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{bahdanau2014neural,
author = {Dzmitry Bahdanau and
Kyunghyun Cho and
Yoshua Bengio},
title = {Neural Machine Translation by Jointly Learning to Align and Translate},
publisher = {International Conference on Learning Representations},
year = {2015}
}
@inproceedings{Jiang2012LearnedPF,
title={Learned Prioritization for Trading Off Accuracy and Speed},
author={Jiarong Jiang and Adam R. Teichert and Hal Daum{\'e} and Jason Eisner},
publisher={Annual Conference on Neural Information Processing Systems},
pages={1340--1348},
year= {2012}
}
@inproceedings{Zheng2020OpportunisticDW,
title={Opportunistic Decoding with Timely Correction for Simultaneous Translation},
author={Renjie Zheng and
Mingbo Ma and
Baigong Zheng and
Kaibo Liu and
Liang Huang},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={437--442},
year={2020}
}
@inproceedings{Ma2019STACLST,
title={STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework},
author={Mingbo Ma and
Liang Huang and
Hao Xiong and
Renjie Zheng and
Kaibo Liu and
Baigong Zheng and
Chuanqiang Zhang and
Zhongjun He and
Hairong Liu and
Xing Li and
Hua Wu and
Haifeng Wang},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={3025--3036},
year={2019}
}
@inproceedings{Gimpel2013ASE,
title={A Systematic Exploration of Diversity in Machine Translation},
author={Kevin Gimpel and Dhruv Batra and Chris Dyer and Gregory Shakhnarovich},
publisher={Conference on Empirical Methods in Natural Language Processing},
pages={1100--1111},
year={2013}
}
@inproceedings{Li2016MutualIA,
title={Mutual Information and Diverse Decoding Improve Neural Machine Translation},
author={Jiwei Li and Dan Jurafsky},
publisher={CoRR},
year={2016},
volume={abs/1601.00372}
}
@inproceedings{Li2016ADO,
title={A Diversity-Promoting Objective Function for Neural Conversation Models},
author={Jiwei Li and
Michel Galley and
Chris Brockett and
Jianfeng Gao and
Bill Dolan},
publisher={Annual Conference of the North American Chapter of the Association for Computational Linguistics},
pages={110--119},
year={2016}
}
@inproceedings{He2018SequenceTS,
title={Sequence to Sequence Mixture Model for Diverse Machine Translation},
author={Xuanli He and Gholamreza Haffari and Mohammad Norouzi},
pages = {583--592},
publisher = {International Conference on Computational Linguistics},
year = {2018}
}
@inproceedings{Shen2019MixtureMF,
title={Mixture Models for Diverse Machine Translation: Tricks of the Trade},
author={Tianxiao Shen and Myle Ott and Michael Auli and Marc'Aurelio Ranzato},
pages = {5719--5728},
publisher = {International Conference on Machine Learning},
year = {2019},
}
@inproceedings{Wu2020GeneratingDT,
title={Generating Diverse Translation from Model Distribution with Dropout},
author={Xuanfu Wu and Yang Feng and Chenze Shao},
pages={1088--1097},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2020}
}
@inproceedings{Sun2020GeneratingDT,
title={Generating Diverse Translation by Manipulating Multi-Head Attention},
author={Zewei Sun and Shujian Huang and Hao Ran Wei and Xin Yu Dai and Jiajun Chen},
publisher={AAAI Conference on Artificial Intelligence},
pages={8976--8983},
year={2020}
}
@inproceedings{Vijayakumar2016DiverseBS,
title={Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models},
author={Ashwin K. Vijayakumar and
Michael Cogswell and
Ramprasaath R. Selvaraju and
Qing Sun and
Stefan Lee and
David J. Crandall and
Dhruv Batra},
publisher={CoRR},
year={2016},
volume={abs/1610.02424}
}
@inproceedings{Liu2014SearchAwareTF,
title={Search-Aware Tuning for Machine Translation},
author={Lemao Liu and
Liang Huang},
publisher={Conference on Empirical Methods in Natural Language Processing},
pages={1942--1952},
year={2014}
}
@inproceedings{Yu2013MaxViolationPA,
title={Max-Violation Perceptron and Forced Decoding for Scalable MT Training},
author={Heng Yu and Liang Huang and Haitao Mi and Kai Zhao},
publisher={Conference on Empirical Methods in Natural Language Processing},
pages={1112--1123},
year={2013}
}
@inproceedings{Stahlberg2019OnNS,
title={On NMT Search Errors and Model Errors: Cat Got Your Tongue?},
author={Felix Stahlberg and
Bill Byrne},
publisher={Conference on Empirical Methods in Natural Language Processing},
pages={3354--3360},
year={2019}
}
@inproceedings{Niehues2017AnalyzingNM,
title={Analyzing Neural MT Search and Model Performance},
author={Jan Niehues and
Eunah Cho and
Thanh-Le Ha and
Alex Waibel},
pages={11--17},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2017}
}
@inproceedings{StahlbergNeural,
title={Neural Machine Translation: A Review},
author={Felix Stahlberg},
publisher={Journal of Artificial Intelligence Research},
year={2020},
volume={69},
pages={343-418}
}
@inproceedings{Ranzato2016SequenceLT,
title={Sequence Level Training with Recurrent Neural Networks},
author={Marc'Aurelio Ranzato and
Sumit Chopra and
Michael Auli and
Wojciech Zaremba},
publisher={International Conference on Learning Representations},
year={2016}
}
@inproceedings{Bengio2015ScheduledSF,
title={Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks},
author={Samy Bengio and
Oriol Vinyals and
Navdeep Jaitly and
Noam Shazeer},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {1171--1179},
year = {2015}
}
@inproceedings{Zhang2019BridgingTG,
title={Bridging the Gap between Training and Inference for Neural Machine Translation},
author={Wen Zhang and Yang Feng and Fandong Meng and Di You and Qun Liu},
pages = {4334--4343},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/ShenCHHWSL16,
author = {Shiqi Shen and
Yong Cheng and
Zhongjun He and
Wei He and
Hua Wu and
Maosong Sun and
Yang Liu},
title = {Minimum Risk Training for Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016},
}
@inproceedings{DBLP:conf/acl/SennrichHB16a,
author = {Rico Sennrich and
Barry Haddow and
Alexandra Birch},
title = {Neural Machine Translation of Rare Words with Subword Units},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016},
}
@inproceedings{DBLP:conf/emnlp/ZensSX12,
author = {Richard Zens and
Daisy Stanton and
Peng Xu},
title = {A Systematic Comparison of Phrase Table Pruning Techniques},
pages = {972--983},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2012}
}
@inproceedings{DBLP:conf/emnlp/JohnsonMFK07,
author = {Howard Johnson and
Joel D. Martin and
George F. Foster and
Roland Kuhn},
title = {Improving Translation Quality by Discarding Most of the Phrasetable},
pages = {967--975},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/emnlp/LingGTB12,
author = {Wang Ling and
Jo{\~{a}}o Gra{\c{c}}a and
Isabel Trancoso and
Alan W. Black},
title = {Entropy-based Pruning for Phrase-based Machine Translation},
pages = {962--971},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2012}
}
@inproceedings{Narang2017BlockSparseRN,
title={Block-Sparse Recurrent Neural Networks},
author={Sharan Narang and Eric Undersander and Gregory Diamos},
publisher={CoRR},
year={2017},
volume={abs/1711.02782}
}
@inproceedings{Gale2019TheSO,
title={The State of Sparsity in Deep Neural Networks},
author={Trevor Gale and
Erich Elsen and
Sara Hooker},
publisher={CoRR},
year={2019},
volume={abs/1902.09574}
}
@inproceedings{Michel2019AreSH,
title={Are Sixteen Heads Really Better than One?},
author = {Paul Michel and
Omer Levy and
Graham Neubig},
title = {Are Sixteen Heads Really Better than One?},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {14014--14024},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-1905-09418,
author = {Elena Voita and
David Talbot and
Fedor Moiseev and
Rico Sennrich and
Ivan Titov},
title = {Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy
Lifting, the Rest Can Be Pruned},
pages = {5797--5808},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019},
}
@inproceedings{Kitaev2020ReformerTE,
author = {Nikita Kitaev and
Lukasz Kaiser and
Anselm Levskaya},
title = {Reformer: The Efficient Transformer},
publisher = {International Conference on Learning Representations},
year = {2020}
}
@inproceedings{Katharopoulos2020TransformersAR,
title={Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention},
author={Angelos Katharopoulos and Apoorv Vyas and Nikolaos Pappas and Franccois Fleuret},
publisher={CoRR},
year={2020},
volume={abs/2006.16236}
}
@inproceedings{xiao2011language,
title ={Language Modeling for Syntax-Based Machine Translation Using Tree Substitution Grammars: A Case Study on Chinese-English Translation},
author ={Xiao, Tong and Zhu, Jingbo and Zhu, Muhua},
volume ={10},
number ={4},
pages ={1--29},
year ={2011},
publisher ={ACM Transactions on Asian Language Information Processing (TALIP)}
}
@inproceedings{Li2009VariationalDF,
title={Variational Decoding for Statistical Machine Translation},
author={Zhifei Li and
Jason Eisner and
Sanjeev Khudanpur},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={593--601},
year={2009}
}
@inproceedings{Bastings2019ModelingLS,
title={Modeling Latent Sentence Structure in Neural Machine Translation},
author={Jasmijn Bastings and
Wilker Aziz and
Ivan Titov and
Khalil Sima'an},
publisher = {CoRR},
volume = {abs/1901.06436},
year = {2019}
}
@inproceedings{Shah2018GenerativeNM,
title={Generative Neural Machine Translation},
author={Harshil Shah and
David Barber},
publisher={Annual Conference on Neural Information Processing Systems},
pages={1353--1362},
year={2018}
}
@inproceedings{Su2018VariationalRN,
title={Variational Recurrent Neural Machine Translation},
author={Jinsong Su and Shan Wu and Deyi Xiong and Yaojie Lu and Xianpei Han and Biao Zhang},
publisher={AAAI Conference on Artificial Intelligence},
pages={5488--5495},
year={2018}
}
@inproceedings{DBLP:journals/corr/GehringAGYD17,
author = {Jonas Gehring and
Michael Auli and
David Grangier and
Denis Yarats and
Yann N. Dauphin},
title = {Convolutional Sequence to Sequence Learning},
publisher = {International Conference on Machine Learning},
volume = {70},
pages = {1243--1252},
year = {2017}
}
@inproceedings{Wei2019ImitationLF,
title={Imitation Learning for Non-Autoregressive Neural Machine Translation},
author={Bingzhen Wei and Mingxuan Wang and Hao Zhou and Junyang Lin and Xu Sun},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages = {1304--1312},
year={2019}
}
@inproceedings{Shao2019RetrievingSI,
title={Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation},
author={Chenze Shao and
Yang Feng and
Jinchao Zhang and
Fandong Meng and
Xilin Chen and
Jie Zhou},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={3013--3024},
year={2019}
}
@inproceedings{Akoury2019SyntacticallyST,
title={Syntactically Supervised Transformers for Faster Neural Machine Translation},
author={Nader Akoury and Kalpesh Krishna and Mohit Iyyer},
pages = {1269--1281},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019},
}
@inproceedings{Guo2020FineTuningBC,
title={Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation},
author={Junliang Guo and
Xu Tan and
Linli Xu and
Tao Qin and
Enhong Chen and
Tie-Yan Liu},
pages = {7839--7846},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2020}
}
@inproceedings{Ran2020LearningTR,
title={Learning to Recover from Multi-Modality Errors for Non-Autoregressive Neural Machine Translation},
author={Qiu Ran and Yankai Lin and Peng Li and Jie Zhou},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={3059--3069},
year={2020}
}
@inproceedings{Liu2020FastBERTAS,
title={FastBERT: a Self-distilling BERT with Adaptive Inference Time},
author={Weijie Liu and
Peng Zhou and
Zhiruo Wang and
Zhe Zhao and
Haotang Deng and
Qi Ju},
pages = {6035--6044},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{Elbayad2020DepthAdaptiveT,
title={Depth-Adaptive Transformer},
author={Maha Elbayad and
Jiatao Gu and
Edouard Grave and
Michael Auli},
publisher={International Conference on Learning Representations},
year={2020}
}
@inproceedings{Lan2020ALBERTAL,
title={ALBERT: A Lite BERT for Self-supervised Learning of Language Representations},
author={Zhenzhong Lan and Mingda Chen and Sebastian Goodman and Kevin Gimpel and Piyush Sharma and Radu Soricut},
publisher={International Conference on Learning Representations},
year={2020}
}
@inproceedings{Han2015LearningBW,
title={Learning both Weights and Connections for Efficient Neural Network},
author={Song Han and
Jeff Pool and
John Tran and
William J. Dally},
publisher={Annual Conference on Neural Information Processing Systems},
pages={1135--1143},
year={2015}
}
@inproceedings{Lee2019SNIPSN,
author = {Namhoon Lee and
Thalaiyasingam Ajanthan and
Philip H. S. Torr},
title = {Snip: single-Shot Network Pruning based on Connection sensitivity},
publisher = {International Conference on Learning Representations},
year = {2019},
}
@inproceedings{Frankle2019TheLT,
title={The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks},
author={Jonathan Frankle and Michael Carbin},
publisher={International Conference on Learning Representations},
year={2019}
}
@inproceedings{Brix2020SuccessfullyAT,
author = {Christopher Brix and
Parnia Bahar and
Hermann Ney},
title = {Successfully Applying the Stabilized Lottery Ticket Hypothesis to
the Transformer Architecture},
pages = {3909--3915},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020},
}
@inproceedings{Liu2019RethinkingTV,
title={Rethinking the Value of Network Pruning},
author={Zhuang Liu and
Mingjie Sun and
Tinghui Zhou and
Gao Huang and
Trevor Darrell},
publisher={ArXiv},
year={2019},
volume={abs/1810.05270}
}
@inproceedings{Liu2017LearningEC,
author = {Zhuang Liu and
Jianguo Li and
Zhiqiang Shen and
Gao Huang and
Shoumeng Yan and
Changshui Zhang},
title = {Learning Efficient Convolutional Networks through Network Slimming},
pages = {2755--2763},
publisher = {{IEEE} International Conference on Computer Vision},
year = {2017}
}
@inproceedings{Banner2018ScalableMF,
title={Scalable Methods for 8-bit Training of Neural Networks},
author={Ron Banner and
Itay Hubara and
Elad Hoffer and
Daniel Soudry},
publisher={Conference on Neural Information Processing Systems},
pages={5151--5159},
year={2018}
}
@inproceedings{Hubara2017QuantizedNN,
title={Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations},
author={Itay Hubara and Matthieu Courbariaux and Daniel Soudry and Ran El-Yaniv and Yoshua Bengio},
publisher={Journal of Machine Learning Reseach},
year={2017},
volume={18},
pages={187:1-187:30}
}
@inproceedings{DBLP:journals/corr/HintonVD15,
author = {Geoffrey E. Hinton and
Oriol Vinyals and
Jeffrey Dean},
title = {Distilling the Knowledge in a Neural Network},
publisher = {CoRR},
volume = {abs/1503.02531},
year = {2015}
}
@inproceedings{Munim2019SequencelevelKD,
title={Sequence-level Knowledge Distillation for Model Compression of Attention-based Sequence-to-sequence Speech Recognition},
author={Raden Mu'az Mun'im and Nakamasa Inoue and Koichi Shinoda},
publisher={{IEEE} International Conference on Acoustics, Speech and Signal Processing},
year={2019},
pages={6151-6155}
}
@inproceedings{Tang2019DistillingTK,
author = {Raphael Tang and
Yao Lu and
Linqing Liu and
Lili Mou and
Olga Vechtomova and
Jimmy Lin},
title = {Distilling Task-Specific Knowledge from {BERT} into Simple Neural
Networks},
publisher = {CoRR},
volume = {abs/1903.12136},
year = {2019}
}
@inproceedings{Jiao2020TinyBERTDB,
author = {Xiaoqi Jiao and
Yichun Yin and
Lifeng Shang and
Xin Jiang and
Xiao Chen and
Linlin Li and
Fang Wang and
Qun Liu},
title = {TinyBERT: Distilling {BERT} for Natural Language Understanding},
pages = {4163--4174},
publisher={Conference on Empirical Methods in Natural Language Processing},
year={2020}
}
@inproceedings{Ghazvininejad2020AlignedCE,
author = {Marjan Ghazvininejad and
Vladimir Karpukhin and
Luke Zettlemoyer and
Omer Levy},
title = {Aligned Cross Entropy for Non-Autoregressive Machine Translation},
publisher = {CoRR},
volume = {abs/2004.01655},
year = {2020},
}
@inproceedings{Shao2020MinimizingTB,
author = {Chenze Shao and
Jinchao Zhang and
Yang Feng and
Fandong Meng and
Jie Zhou},
title = {Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural
Machine Translation},
pages = {198--205},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2020},
}
@inproceedings{Ma2019FlowSeqNC,
title={FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow},
author={Xuezhe Ma and
Chunting Zhou and
Xian Li and
Graham Neubig and
Eduard H. Hovy},
publisher={Conference on Empirical Methods in Natural Language Processing},
pages={4281--4291},
year={2019}
}
@inproceedings{Guo2019NonAutoregressiveNM,
title={Non-Autoregressive Neural Machine Translation with Enhanced Decoder Input},
author={Junliang Guo and
Xu Tan and
Di He and
Tao Qin and
Linli Xu and
Tie-Yan Liu},
pages={3723--3730},
publisher={AAAI Conference on Artificial Intelligence},
year={2019}
}
@inproceedings{Ran2019GuidingNN,
author = {Qiu Ran and
Yankai Lin and
Peng Li and
Jie Zhou},
title = {Guiding Non-Autoregressive Neural Machine Translation Decoding with
Reordering Information},
publisher = {CoRR},
volume = {abs/1911.02215},
year = {2019}
}
@inproceedings{vaswani2017attention,
title={Attention is All You Need},
author={Ashish {Vaswani} and Noam {Shazeer} and Niki {Parmar} and Jakob {Uszkoreit} and Llion {Jones} and Aidan N. {Gomez} and Lukasz {Kaiser} and Illia {Polosukhin}},
publisher={International Conference on Neural Information Processing},
pages={5998--6008},
year={2017}
}
@inproceedings{Gu2017NonAutoregressiveNM,
author = {Jiatao Gu and
James Bradbury and
Caiming Xiong and
Victor O. K. Li and
Richard Socher},
title = {Non-Autoregressive Neural Machine Translation},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{Zhou2020UnderstandingKD,
title={Understanding Knowledge Distillation in Non-autoregressive Machine Translation},
author={Chunting Zhou and Graham Neubig and Jiatao Gu},
publisher={ArXiv},
year={2020},
volume={abs/1911.02727}
}
@inproceedings{Wang2019NonAutoregressiveMT,
title={Non-Autoregressive Machine Translation with Auxiliary Regularization},
author={Yiren Wang and
Fei Tian and
Di He and
Tao Qin and
ChengXiang Zhai and
Tie-Yan Liu},
publisher={AAAI Conference on Artificial Intelligence},
pages={5377--5384},
year={2019}
}
@inproceedings{Kaiser2018FastDI,
title={Fast Decoding in Sequence Models using Discrete Latent Variables},
author={Łukasz Kaiser and Aurko Roy and Ashish Vaswani and Niki Parmar and Samy Bengio and Jakob Uszkoreit and Noam Shazeer},
publisher={International Conference on Machine Learning},
pages={2395--2404},
year={2018}
}
@inproceedings{Tu2020ENGINEEI,
title={ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation},
author={Lifu Tu and Richard Yuanzhe Pang and Sam Wiseman and Kevin Gimpel},
pages={2819--2826},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2020}
}
@inproceedings{Shu2020LatentVariableNN,
title={Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference using a Delta Posterior},
author={Raphael Shu and Jason Lee and Hideki Nakayama and Kyunghyun Cho},
publisher={AAAI Conference on Artificial Intelligence},
pages={8846--8853},
year={2020}
}
@inproceedings{Li2019HintBasedTF,
title={Hint-Based Training for Non-Autoregressive Machine Translation},
author={Zhuohan Li and
Zi Lin and
Di He and
Fei Tian and
Tao Qin and
Liwei Wang and
Tie-Yan Liu},
publisher={Conference on Empirical Methods in Natural Language Processing},
pages={5707--5712},
year={2019}
}
@inproceedings{Ho2016ModelFreeIL,
title={Model-Free Imitation Learning with Policy Optimization},
author={Jonathan Ho and
Jayesh K. Gupta and
Stefano Ermon},
publisher={International Conference on Machine Learning},
pages={2760--2769},
year={2016}
}
@inproceedings{Ho2016GenerativeAI,
title={Generative Adversarial Imitation Learning},
author={Jonathan Ho and Stefano Ermon},
publisher={Annual Conference on Neural Information Processing Systems},
pages={4565--4573},
year={2016}
}
@inproceedings{Duan2017OneShotIL,
title={One-Shot Imitation Learning},
author={Yan Duan and Marcin Andrychowicz and Bradly C. Stadie and Jonathan Ho and Jonas Schneider and Ilya Sutskever and Pieter Abbeel and Wojciech Zaremba},
publisher={CoRR},
year={2017},
volume={abs/1703.07326}
}
@inproceedings{Wang2018SemiAutoregressiveNM,
title={Semi-Autoregressive Neural Machine Translation},
author={Chunqi Wang and
Ji Zhang and
Haiqing Chen},
publisher={Conference on Empirical Methods in Natural Language Processing},
pages={479--488},
year={2018}
}
@inproceedings{Ghazvininejad2019MaskPredictPD,
title={Mask-Predict: Parallel Decoding of Conditional Masked Language Models},
author={Marjan Ghazvininejad and Omer Levy and Yinhan Liu and Luke Zettlemoyer},
publisher={Conference on Empirical Methods in Natural Language Processing},
pages={6111--6120},
year={2019}
}
@inproceedings{Kasai2020NonAutoregressiveMT,
title={Non-Autoregressive Machine Translation with Disentangled Context Transformer},
author={Jungo Kasai and J. Cross and Marjan Ghazvininejad and Jiatao Gu},
publisher={arXiv: Computation and Language},
year={2020}
}
@inproceedings{Zhou2019SynchronousBN,
title={Synchronous Bidirectional Neural Machine Translation},
author={Long Zhou and
Jiajun Zhang and
Chengqing Zong},
publisher={Transactions of the Association for Computational Linguistics},
year={2019},
volume={7},
pages={91-105}
}
@inproceedings{devlin2019bert,
title={Bert: Pre-training of deep bidirectional transformers for language understanding},
author={Devlin Jacob and Chang Ming-Wei and Lee Kenton and Toutanova Kristina},
year={2019},
pages = {4171--4186},
publisher = {Annual Meeting of the Association for Computational Linguistics},
}
@inproceedings{Feng2016ImprovingAM,
title={Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation},
author={Shi Feng and Shujie Liu and Nan Yang and Mu Li and Ming Zhou and Kenny Q. Zhu},
publisher={International Conference on Computational Linguistics},
pages={3082--3092},
year={2016}
}
@inproceedings{TuModeling,
author = {Zhaopeng Tu and
Zhengdong Lu and
Yang Liu and
Xiaohua Liu and
Hang Li},
title = {Modeling Coverage for Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{Wu2016GooglesNM,
title={Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation},
author = {Yonghui Wu and
Mike Schuster and
Zhifeng Chen and
Quoc V. Le and
Mohammad Norouzi and
Wolfgang Macherey and
Maxim Krikun and
Yuan Cao and
Qin Gao and
Klaus Macherey and
Jeff Klingner and
Apurva Shah and
Melvin Johnson and
Xiaobing Liu and
Lukasz Kaiser and
Stephan Gouws and
Yoshikiyo Kato and
Taku Kudo and
Hideto Kazawa and
Keith Stevens and
George Kurian and
Nishant Patil and
Wei Wang and
Cliff Young and
Jason Smith and
Jason Riesa and
Alex Rudnick and
Oriol Vinyals and
Greg Corrado and
Macduff Hughes and
Jeffrey Dean},
publisher = {CoRR},
year={2016},
volume={abs/1609.08144}
}
@inproceedings{li-etal-2018-simple,
author = {Yanyang Li and
Tong Xiao and
Yinqiao Li and
Qiang Wang and
Changming Xu and
Jingbo Zhu},
title = {A Simple and Effective Approach to Coverage-Aware Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {292--297},
year = {2018}
}
@inproceedings{Peris2017InteractiveNM,
title={Interactive neural machine translation},
author={{\'A}lvaro Peris and Miguel Domingo and F. Casacuberta},
publisher={Computer Speech and Language},
year={2017},
volume={45},
pages={201-220}
}
@inproceedings{Peris2018ActiveLF,
title={Active Learning for Interactive Neural Machine Translation of Data Streams},
author={{\'A}lvaro Peris and Francisco Casacuberta},
publisher={The SIGNLL Conference on Computational Natural Language Learning},
pages={151--160},
year={2018}
}
@inproceedings{Xiao2016ALA,
title={A Loss-Augmented Approach to Training Syntactic Machine Translation Systems},
author={Tong Xiao and Derek F. Wong and Jingbo Zhu},
publisher={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
year={2016},
volume={24},
pages={2069-2083}
}
@inproceedings{DBLP:conf/acl/JeanCMB15,
author = {S{\'{e}}bastien Jean and
KyungHyun Cho and
Roland Memisevic and
Yoshua Bengio},
title = {On Using Very Large Target Vocabulary for Neural Machine Translation},
pages = {1--10},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{61115,
author={Jianhua Lin},
publisher={IEEE Transactions on Information Theory},
title={Divergence measures based on the Shannon entropy},
year={1991},
volume={37},
number={1},
pages={145-151}
}
@inproceedings{DBLP:conf/aaai/DabreF19,
author = {Raj Dabre and
Atsushi Fujita},
title = {Recurrent Stacking of Layers for Compact Neural Machine Translation
Models},
pages = {6292--6299},
publisher = { AAAI Conference on Artificial Intelligence},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-1805-00631,
author = {Biao Zhang and
Deyi Xiong and
Jinsong Su},
title = {Accelerating Neural Transformer via an Average Attention Network},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {1789--1798},
year = {2018},
}
@inproceedings{Wu2019PayLA,
author = {Felix Wu and
Angela Fan and
Alexei Baevski and
Yann N. Dauphin and
Michael Auli},
title = {Pay Less Attention with Lightweight and Dynamic Convolutions},
publisher = {International Conference on Learning Representations},
year = {2019},
}
@inproceedings{Xiao2019SharingAW,
author = {Tong Xiao and
Yinqiao Li and
Jingbo Zhu and
Zhengtao Yu and
Tongran Liu},
title = {Sharing Attention Weights for Fast Transformer},
publisher = {International Joint Conference on Artificial Intelligence},
pages = {5292--5298},
year = {2019}
}
@inproceedings{Chen2018TheBO,
author = {Mia Xu Chen and
Orhan Firat and
Ankur Bapna and
Melvin Johnson and
Wolfgang Macherey and
George F. Foster and
Llion Jones and
Mike Schuster and
Noam Shazeer and
Niki Parmar and
Ashish Vaswani and
Jakob Uszkoreit and
Lukasz Kaiser and
Zhifeng Chen and
Yonghui Wu and
Macduff Hughes},
title = {The Best of Both Worlds: Combining Recent Advances in Neural Machine
Translation},
pages = {76--86},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:journals/corr/abs-1906-00532,
author = {Aishwarya Bhandare and
Vamsi Sripathi and
Deepthi Karkada and
Vivek Menon and
Sun Choi and
Kushal Datta and
Vikram Saletore},
title = {Efficient 8-Bit Quantization of Transformer Neural Machine Language
Translation Model},
publisher = {CoRR},
volume = {abs/1906.00532},
year = {2019}
}
@inproceedings{DBLP:conf/cvpr/JacobKCZTHAK18,
author = {Benoit Jacob and
Skirmantas Kligys and
Bo Chen and
Menglong Zhu and
Matthew Tang and
Andrew G. Howard and
Hartwig Adam and
Dmitry Kalenichenko},
title = {Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only
Inference},
publisher = {{IEEE} Conference on Computer Vision and Pattern Recognition},
pages = {2704--2713},
year = {2018}
}
@inproceedings{DBLP:journals/corr/abs-1910-10485,
author = {Gabriele Prato and
Ella Charlaix and
Mehdi Rezagholizadeh},
title = {Fully Quantized Transformer for Improved Translation},
publisher = {CoRR},
volume = {abs/1910.10485},
year = {2019}
}
@inproceedings{DBLP:conf/nips/HubaraCSEB16,
author = {Itay Hubara and
Matthieu Courbariaux and
Daniel Soudry and
Ran El-Yaniv and
Yoshua Bengio},
title = {Binarized Neural Networks},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {4107--4115},
year = {2016}
}
@inproceedings{DBLP:journals/jcss/FreundS97,
author = {Yoav Freund and
Robert E. Schapire},
title = {A Decision-Theoretic Generalization of On-Line Learning and an Application
to Boosting},
publisher = {Journal of Computer and System Sciences},
volume = {55},
number = {1},
pages = {119--139},
year = {1997}
}
@inproceedings{DBLP:conf/acl/XiaoZZW10,
author = {Tong Xiao and
Jingbo Zhu and
Muhua Zhu and
Huizhen Wang},
title = {Boosting-Based System Combination for Machine Translation},
pages = {739--748},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2010}
}
@inproceedings{DBLP:conf/icassp/SimBGSW07,
author = {Khe Chai Sim and
William J. Byrne and
Mark J. F. Gales and
Hichem Sahbi and
Philip C. Woodland},
title = {Consensus Network Decoding for Statistical Machine Translation System
Combination},
publisher = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing},
pages = {105--108},
year = {2007}
}
@inproceedings{DBLP:conf/acl/RostiMS07,
author = {Antti-Veikko I. Rosti and
Spyridon Matsoukas and
Richard M. Schwartz},
title = {Improved Word-Level System Combination for Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/wmt/RostiZMS08,
author = {Antti-Veikko I. Rosti and
Bing Zhang and
Spyros Matsoukas and
Richard M. Schwartz},
title = {Incremental Hypothesis Alignment for Building Confusion Networks with
Application to Machine Translation System Combination},
publisher = {Proceedings of the Third Workshop on Statistical Machine Translation},
pages = {183--186},
year = {2008}
}
@inproceedings{DBLP:conf/emnlp/DuanLXZ09,
author = {Nan Duan and
Mu Li and
Tong Xiao and
Ming Zhou},
title = {The Feature Subspace Method for SMT System Combination},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {1096--1104},
year = {2009}
}
@inproceedings{DBLP:journals/corr/LiMJ16,
author = {Jiwei Li and
Will Monroe and
Dan Jurafsky},
title = {A Simple, Fast Diverse Decoding Algorithm for Neural Generation},
publisher = {CoRR},
volume = {abs/1611.08562},
year = {2016}
}
@inproceedings{xiao2013bagging,
title ={Bagging and boosting statistical machine translation systems},
author ={Tong Xiao and Jingbo Zhu and Tongran Liu },
publisher ={Artificial Intelligence},
volume ={195},
pages ={496--527},
year ={2013}
}
@inproceedings{DBLP:conf/emnlp/TrombleKOM08,
author = {Roy Tromble and
Shankar Kumar and
Franz Josef Och and
Wolfgang Macherey},
title = {Lattice Minimum Bayes-Risk Decoding for Statistical Machine Translation},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {620--629},
year = {2008}
}
@inproceedings{DBLP:conf/aaai/SuTXJSL17,
author = {Jinsong Su and
Zhixing Tan and
Deyi Xiong and
Rongrong Ji and
Xiaodong Shi and
Yang Liu},
title = {Lattice-Based Recurrent Neural Network Encoders for Neural Machine
Translation},
publisher = {AAAI Conference on Artificial Intelligence},
pages = {3302--3308},
year = {2017}
}
@inproceedings{Shaw2018SelfAttentionWR,
author = {Peter Shaw and
Jakob Uszkoreit and
Ashish Vaswani},
title = {Self-Attention with Relative Position Representations},
publisher = {Proceedings of the Human Language Technology Conference of
the North American Chapter of the Association for Computational Linguistics},
pages = {464--468},
year = {2018}
}
@inproceedings{WangLearning,
author = {Qiang Wang and
Bei Li and
Tong Xiao and
Jingbo Zhu and
Changliang Li and
Derek F. Wong and
Lidia S. Chao},
title = {Learning Deep Transformer Models for Machine Translation},
pages = {1810--1822},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/iclr/FanGJ20,
author = {Angela Fan and
Edouard Grave and
Armand Joulin},
title = {Reducing Transformer Depth on Demand with Structured Dropout},
publisher = {International Conference on Learning Representations},
year = {2020}
}
@inproceedings{DBLP:conf/emnlp/WangXZ20,
author = {Qiang Wang and
Tong Xiao and
Jingbo Zhu},
title = {Training Flexible Depth Model by Multi-Task Learning for Neural Machine
Translation},
pages = {4307--4312},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-2002-02925,
author = {Canwen Xu and
Wangchunshu Zhou and
Tao Ge and
Furu Wei and
Ming Zhou},
title = {BERT-of-Theseus: Compressing {BERT} by Progressive Module Replacing},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2020}
}
@inproceedings{DBLP:conf/iclr/BaevskiA19,
author = {Alexei Baevski and
Michael Auli},
title = {Adaptive Input Representations for Neural Language Modeling},
publisher = {arXiv preprint arXiv:1809.10853},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-2006-04768,
author = {Sinong Wang and
Belinda Z. Li and
Madian Khabsa and
Han Fang and
Hao Ma},
title = {Linformer: Self-Attention with Linear Complexity},
publisher = {CoRR},
volume = {abs/2006.04768},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-1911-12385,
author = {Sachin Mehta and
Rik Koncel-Kedziorski and
Mohammad Rastegari and
Hannaneh Hajishirzi},
title = {DeFINE: DEep Factorized INput Word Embeddings for Neural Sequence
Modeling},
publisher = {CoRR},
volume = {abs/1911.12385},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-1906-09777,
author = {Xindian Ma and
Peng Zhang and
Shuai Zhang and
Nan Duan and
Yuexian Hou and
Dawei Song and
Ming Zhou},
title = {A Tensorized Transformer for Language Modeling},
publisher = {CoRR},
volume = {abs/1906.09777},
year = {2019}
}
@inproceedings{DBLP:conf/nips/YangLSL19,
author = {Zhilin Yang and
Thang Luong and
Ruslan Salakhutdinov and
Quoc V. Le},
title = {Mixtape: Breaking the Softmax Bottleneck Efficiently},
publisher = {Conference on Neural Information Processing Systems},
pages = {15922--15930},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-2006-10369,
author = {Jungo Kasai and
Nikolaos Pappas and
Hao Peng and
James Cross and
Noah A. Smith},
title = {Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff
in Machine Translation},
publisher = {CoRR},
volume = {abs/2006.10369},
year = {2020}
}
@inproceedings{DBLP:conf/aclnmt/HuLLLLWXZ20,
author = {Chi Hu and
Bei Li and
Yinqiao Li and
Ye Lin and
Yanyang Li and
Chenglong Wang and
Tong Xiao and
Jingbo Zhu},
title = {The NiuTrans System for WNGT 2020 Efficiency Task},
pages = {204--210},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-2010-02416,
author = {Yi-Te Hsu and
Sarthak Garg and
Yi-Hsiu Liao and
Ilya Chatsviorkin},
title = {Efficient Inference For Neural Machine Translation},
publisher = {CoRR},
volume = {abs/2010.02416},
year = {2020}
}
@inproceedings{Vaswani2018Tensor2TensorFN,
author = {Ashish Vaswani and
Samy Bengio and
Eugene Brevdo and
Fran{\c{c}}ois Chollet and
Aidan N. Gomez and
Stephan Gouws and
Llion Jones and
Lukasz Kaiser and
Nal Kalchbrenner and
Niki Parmar and
Ryan Sepassi and
Noam Shazeer and
Jakob Uszkoreit},
title = {Tensor2Tensor for Neural Machine Translation},
pages = {193--199},
publisher = {Association for Machine Translation in the Americas},
year = {2018}
}
@inproceedings{Sun2019BaiduNM,
title={Baidu Neural Machine Translation Systems for WMT19},
author = {Meng Sun and
Bojian Jiang and
Hao Xiong and
Zhongjun He and
Hua Wu and
Haifeng Wang},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages = {374--381},
year={2019}
}
@inproceedings{Wang2018TencentNM,
title={Tencent Neural Machine Translation Systems for WMT18},
author={Mingxuan Wang and
Li Gong and
Wenhuan Zhu and
Jun Xie and
Chao Bian},
publisher={Annual Meeting of the Association for Computational Linguistics},
pages={522--527},
year={2018}
}
@inproceedings{Bi2019MultiagentLF,
title={Multi-agent Learning for Neural Machine Translation},
author={Tianchi Bi and
Hao Xiong and
Zhongjun He and
Hua Wu and
Haifeng Wang},
publisher={arXiv preprint arXiv:1909.01101},
year={2019}
}
@inproceedings{DBLP:conf/aclnmt/KoehnK17,
author = {Philipp Koehn and
Rebecca Knowles},
title = {Six Challenges for Neural Machine Translation},
pages = {28--39},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{Held2013AppliedSI,
title={Applied statistical inference},
author={Leonhard Held and Saban{\'e}s Bov{\'e}, D},
volume={10},
number={978-3},
pages={16},
year={2014},
publisher={Springer}
}
@inproceedings{Zhang2016VariationalNM,
title={Variational Neural Machine Translation},
author = {Biao Zhang and
Deyi Xiong and
Jinsong Su and
Hong Duan and
Min Zhang},
pages = {521--530},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{Silvey2018StatisticalI,
title={Statistical Inference},
author={S. D. Silvey},
publisher={Encyclopedia of Social Network Analysis and Mining},
year={2018}
}
@inproceedings{Cheong2019transformersZ,
title={transformers.zip : Compressing Transformers with Pruning and Quantization},
author={Robin Cheong and Robel Daniel},
publisher={Stanford University},
year={2019}
}
@inproceedings{Beal2003VariationalAF,
title={Variational algorithms for approximate Bayesian inference},
author={Matthew J. Beal},
publisher={University College London},
year={2003}
}
@inproceedings{Gage1994ANA,
title={A new algorithm for data compression},
author={P. Gage},
publisher={The C Users Journal archive},
year={1994},
volume={12},
pages={23-38}
}
@inproceedings{Eisner2011LearningST,
title={Learning Speed-Accuracy Tradeoffs in Nondeterministic Inference Algorithms},
author={J. Eisner and Hal Daum{\'e}},
publisher={Annual Conference on Neural Information Processing Systems},
year={2011}
}
@inproceedings{Kazimi2017CoverageFC,
title={Coverage for Character Based Neural Machine Translation},
author={M. Kazimi and Marta R. Costa-juss{\`a}},
publisher={arXiv preprint arXiv:1810.02340},
year={2017},
volume={59},
pages={99-106}
}
@inproceedings{zhang-EtAl:2020:WMT,
author = {Zhang, Yuhao and
Wang, Ziyang and
Cao, Runzhe and
Wei, Binghao and
Shan, Weiqiao and
Zhou, Shuhan and
Reheman, Abudurexiti and
Zhou, Tao and
Zeng, Xin and
Wang, Laohu and
Mu, Yongyu and
Zhang, Jingnan and
Liu, Xiaoqian and
Zhou, Xuanjun and
Li, Yinqiao and
Li, Bei and
Xiao, Tong and
Zhu, Jingbo},
title = {The NiuTrans Machine Translation Systems for WMT20},
month = {November},
year = {2020},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {336--343}
}
@inproceedings{DBLP:conf/nips/MehriS18,
author = {Shikib Mehri and
Leonid Sigal},
title = {Middle-Out Decoding},
publisher = {Conference on Neural Information Processing Systems},
pages = {5523--5534},
year = {2018}
}
%%%%% chapter 14------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 15------------------------------------------------------
@inproceedings{DBLP:conf/cvpr/YuYR18,
author = {Xin Yu and
Zhiding Yu and
Srikumar Ramalingam},
title = {Learning Strict Identity Mappings in Deep Residual Networks},
pages = {4432--4440},
publisher = {{IEEE} Conference on Computer Vision and Pattern Recognition},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/ZhangTS19,
author = {Biao Zhang and
Ivan Titov and
Rico Sennrich},
title = {Improving Deep Transformer with Depth-Scaled Initialization and Merged
Attention},
pages = {898--909},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/eccv/HeZRS16,
author = {Kaiming He and
Xiangyu Zhang and
Shaoqing Ren and
Jian Sun},
title = {Identity Mappings in Deep Residual Networks},
volume = {9908},
pages = {630--645},
publisher = {European Conference on Computer Vision},
year = {2016}
}
@inproceedings{Ottfairseq,
author = {Myle Ott and
Sergey Edunov and
Alexei Baevski and
Angela Fan and
Sam Gross and
Nathan Ng and
David Grangier and
Michael Auli},
title = {fairseq: {A} Fast, Extensible Toolkit for Sequence Modeling},
pages = {48--53},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{KleinOpenNMT,
author = {Guillaume Klein and
Yoon Kim and
Yuntian Deng and
Jean Senellart and
Alexander M. Rush},
title = {OpenNMT: Open-Source Toolkit for Neural Machine Translation},
pages = {67--72},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/acl/WuWXTGQLL19,
author = {Lijun Wu and
Yiren Wang and
Yingce Xia and
Fei Tian and
Fei Gao and
Tao Qin and
Jianhuang Lai and
Tie-Yan Liu},
title = {Depth Growing for Neural Machine Translation},
pages = {5558--5563},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/cvpr/HuangLMW17,
author = {Gao Huang and
Zhuang Liu and
Laurens van der Maaten and
Kilian Q. Weinberger},
title = {Densely Connected Convolutional Networks},
pages = {2261--2269},
publisher = {{IEEE} Conference on Computer Vision and Pattern Recognition},
year = {2017}
}
@inproceedings{DBLP:journals/corr/GreffSS16,
author = {Klaus Greff and
Rupesh Kumar Srivastava and
J{\"{u}}rgen Schmidhuber},
title = {Highway and Residual Networks learn Unrolled Iterative Estimation},
publisher = {International Conference on Learning Representations},
year = {2017}
}
@inproceedings{Bapna2018TrainingDN,
author = {Ankur Bapna and
Mia Xu Chen and
Orhan Firat and
Yuan Cao and
Yonghui Wu},
title = {Training Deeper Neural Machine Translation Models with Transparent
Attention},
pages = {3028--3033},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{WangLearning,
author = {Qiang Wang and
Bei Li and
Tong Xiao and
Jingbo Zhu and
Changliang Li and
Derek F. Wong and
Lidia S. Chao},
title = {Learning Deep Transformer Models for Machine Translation},
pages = {1810--1822},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-2002-04745,
author = {Ruibin Xiong and
Yunchang Yang and
Di He and
Kai Zheng and
Shuxin Zheng and
Chen Xing and
Huishuai Zhang and
Yanyan Lan and
Liwei Wang and
Tie-Yan Liu},
title = {On Layer Normalization in the Transformer Architecture},
publisher = {International Conference on Machine Learning},
volume = {abs/2002.04745},
year = {2020}
}
@inproceedings{DBLP:conf/emnlp/LiuLGCH20,
author = {Liyuan Liu and
Xiaodong Liu and
Jianfeng Gao and
Weizhu Chen and
Jiawei Han},
title = {Understanding the Difficulty of Training Transformers},
pages = {5747--5763},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:journals/corr/HeZRS15,
author = {Kaiming He and
Xiangyu Zhang and
Shaoqing Ren and
Jian Sun},
title = {Deep Residual Learning for Image Recognition},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
pages = {770--778},
year = {2016},
}
@inproceedings{Ba2016LayerN,
author = {Lei Jimmy Ba and
Jamie Ryan Kiros and
Geoffrey E. Hinton},
title = {Layer Normalization},
publisher = {CoRR},
volume = {abs/1607.06450},
year = {2016}
}
@inproceedings{Vaswani2018Tensor2TensorFN,
author = {Ashish Vaswani and
Samy Bengio and
Eugene Brevdo and
Fran{\c{c}}ois Chollet and
Aidan N. Gomez and
Stephan Gouws and
Llion Jones and
Lukasz Kaiser and
Nal Kalchbrenner and
Niki Parmar and
Ryan Sepassi and
Noam Shazeer and
Jakob Uszkoreit},
title = {Tensor2Tensor for Neural Machine Translation},
pages = {193--199},
publisher = {Association for Machine Translation in the Americas},
year = {2018}
}
@inproceedings{Dou2019DynamicLA,
author = {Zi-Yi Dou and
Zhaopeng Tu and
Xing Wang and
Longyue Wang and
Shuming Shi and
Tong Zhang},
title = {Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement},
pages = {86--93},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2019}
}
@inproceedings{Wang2018MultilayerRF,
title={Multi-layer Representation Fusion for Neural Machine Translation},
author={Qiang Wang and Fuxue Li and Tong Xiao and Yanyang Li and Yinqiao Li and Jingbo Zhu},
publisher={International Conference on Computational Linguistics},
year={2018},
volume={abs/2002.06714}
}
@inproceedings{Dou2018ExploitingDR,
author = {Zi-Yi Dou and
Zhaopeng Tu and
Xing Wang and
Shuming Shi and
Tong Zhang},
title = {Exploiting Deep Representations for Neural Machine Translation},
pages = {4253--4262},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:journals/corr/LinFSYXZB17,
author = {Zhouhan Lin and
Minwei Feng and
C{\'{\i}}cero Nogueira dos Santos and
Mo Yu and
Bing Xiang and
Bowen Zhou and
Yoshua Bengio},
title = {A Structured Self-Attentive Sentence Embedding},
publisher = {International Conference on Learning Representations},
year = {2017},
}
@inproceedings{DBLP:conf/nips/SrivastavaGS15,
author = {Rupesh Kumar Srivastava and
Klaus Greff and
J{\"{u}}rgen Schmidhuber},
title = {Training Very Deep Networks},
publisher = {Conference on Neural Information Processing Systems},
pages = {2377--2385},
year = {2015}
}
@inproceedings{DBLP:conf/icml/BalduzziFLLMM17,
author = {David Balduzzi and
Marcus Frean and
Lennox Leary and
J. P. Lewis and
Kurt Wan-Duo Ma and
Brian McWilliams},
title = {The Shattered Gradients Problem: If resnets are the answer, then what
is the question?},
publisher = {International Conference on Machine Learning},
volume = {70},
pages = {342--350},
year = {2017}
}
@inproceedings{DBLP:conf/icml/Allen-ZhuLS19,
author = {Zeyuan Allen-Zhu and
Yuanzhi Li and
Zhao Song},
title = {A Convergence Theory for Deep Learning via Over-Parameterization},
publisher = {International Conference on Machine Learning},
volume = {97},
pages = {242--252},
year = {2019}
}
@inproceedings{DBLP:conf/icml/DuLL0Z19,
author = {Simon S. Du and
Jason D. Lee and
Haochuan Li and
Liwei Wang and
Xiyu Zhai},
title = {Gradient Descent Finds Global Minima of Deep Neural Networks},
publisher = {International Conference on Machine Learning},
volume = {97},
pages = {1675--1685},
year = {2019}
}
@inproceedings{pmlr-v9-glorot10a,
author = {Xavier Glorot and
Yoshua Bengio},
title = {Understanding the difficulty of training deep feedforward neural networks},
publisher = {International Conference on Artificial Intelligence and Statistics},
volume = {9},
pages = {249--256},
year = {2010}
}
@inproceedings{DBLP:conf/iccv/HeZRS15,
author = {Kaiming He and
Xiangyu Zhang and
Shaoqing Ren and
Jian Sun},
title = {Delving Deep into Rectifiers: Surpassing Human-Level Performance on
ImageNet Classification},
pages = {1026--1034},
publisher = {IEEE International Conference on Computer Vision},
year = {2015}
}
@inproceedings{huang2020improving,
title={Improving Transformer Optimization Through Better Initialization},
author={Xiao Shi {Huang} and Juan {Perez} and Jimmy {Ba} and Maksims {Volkovs}},
publisher = {International Conference on Machine Learning},
year={2020}
}
@inproceedings{DBLP:conf/iclr/ZophL17,
author = {Barret Zoph and
Quoc V. Le},
title = {Neural Architecture Search with Reinforcement Learning},
publisher = {International Conference on Learning Representations},
year = {2017}
}
@inproceedings{DBLP:conf/cvpr/ZophVSL18,
author = {Barret Zoph and
Vijay Vasudevan and
Jonathon Shlens and
Quoc V. Le},
title = {Learning Transferable Architectures for Scalable Image Recognition},
pages = {8697--8710},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2018}
}
@inproceedings{Real2019AgingEF,
title={Aging Evolution for Image Classifier Architecture Search},
author={Esteban Real and Alok Aggarwal and Yanping Huang and Quoc V. Le },
publisher={AAAI Conference on Artificial Intelligence},
year={2019}
}
@inproceedings{DBLP:conf/icml/SoLL19,
author = {David R. So and
Quoc V. Le and
Chen Liang},
title = {The Evolved Transformer},
volume = {97},
pages = {5877--5886},
publisher = {International Conference on Machine Learning},
year = {2019}
}
@inproceedings{DBLP:conf/icga/MillerTH89,
author = {Geoffrey F. Miller and
Peter M. Todd and
Shailesh U. Hegde},
title = {Designing Neural Networks using Genetic Algorithms},
pages = {379--384},
publisher = {International Conference on Genetic Algorithms},
year = {1989}
}
@inproceedings{mandischer1993representation,
title={Representation and evolution of neural networks},
author={Mandischer, Martin},
publisher={Artificial Neural Nets and Genetic Algorithms},
pages={643--649},
year={1993}
}
@inproceedings{koza1991genetic,
title={Genetic generation of both the weights and architecture for a neural network},
author={Koza, John R and Rice, James P},
publisher={international joint conference on neural networks},
volume={2},
pages={397--404},
year={1991}
}
@inproceedings{DBLP:conf/ijcnn/Dodd90,
author = {Dodd Nigel},
title = {Optimisation of network structure using genetic techniques},
publisher = {International Joint Conference on Neural Networks, San
Diego, CA, USA, June 17-21, 1990},
pages = {965--970},
year = {1990}
}
@inproceedings{DBLP:conf/nips/HarpSG89,
author = {Steven A. Harp and
Tariq Samad and
Aloke Guha},
title = {Designing Application-Specific Neural Networks Using the Genetic Algorithm},
publisher = {Advances in Neural Information Processing Systems},
pages = {447--454},
year = {1989}
}
@inproceedings{DBLP:journals/compsys/Kitano90,
author = {Hiroaki Kitano},
title = {Designing Neural Networks Using Genetic Algorithms with Graph Generation
System},
publisher = {Complex Systems},
volume = {4},
number = {4},
year = {1990}
}
@inproceedings{DBLP:conf/icec/SantosD94,
author = {Jos{\'{e}} Santos Reyes and
Richard J. Duro},
title = {Evolutionary Generation and Training of Recurrent Artificial Neural
Networks},
pages = {759--763},
publisher = {IEEE Conference on Evolutionary Computation},
year = {1994}
}
@inproceedings{DBLP:conf/nips/LuoTQCL18,
author = {Renqian Luo and
Fei Tian and
Tao Qin and
Enhong Chen and
Tie-Yan Liu},
title = {Neural Architecture Optimization},
publisher = {Advances in Neural Information Processing Systems},
pages = {7827--7838},
year = {2018}
}
@inproceedings{DBLP:conf/icml/PhamGZLD18,
author = {Hieu Pham and
Melody Y. Guan and
Barret Zoph and
Quoc V. Le and
Jeff Dean},
title = {Efficient Neural Architecture Search via Parameter Sharing},
volume = {80},
pages = {4092--4101},
publisher = {International Conference on Machine Learning},
year = {2018}
}
@inproceedings{DBLP:conf/iclr/LiuSY19,
author = {Hanxiao Liu and
Karen Simonyan and
Yiming Yang},
title = {{DARTS:} Differentiable Architecture Search},
publisher = {International Conference on Learning Representations},
year = {2019}
}
@inproceedings{DBLP:conf/acl/LiHZXJXZLL20,
author = {Yinqiao Li and
Chi Hu and
Yuhao Zhang and
Nuo Xu and
Yufan Jiang and
Tong Xiao and
Jingbo Zhu and
Tongran Liu and
Changliang Li},
title = {Learning Architectures from an Extended Search Space for Language
Modeling},
pages = {6629--6639},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/emnlp/JiangHXZZ19,
author = {Yufan Jiang and
Chi Hu and
Tong Xiao and
Chunliang Zhang and
Jingbo Zhu},
title = {Improved Differentiable Architecture Search for Language Modeling
and Named Entity Recognition},
pages = {3583--3588},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/aaai/RealAHL19,
author = {Esteban Real and
Alok Aggarwal and
Yanping Huang and
Quoc V. Le},
title = {Regularized Evolution for Image Classifier Architecture Search},
pages = {4780--4789},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2019}
}
@inproceedings{DBLP:conf/icml/RealMSSSTLK17,
author = {Esteban Real and
Sherry Moore and
Andrew Selle and
Saurabh Saxena and
Yutaka Leon Suematsu and
Jie Tan and
Quoc V. Le and
Alexey Kurakin},
title = {Large-Scale Evolution of Image Classifiers},
volume = {70},
pages = {2902--2911},
publisher = {International Conference on Machine Learning},
year = {2017}
}
@inproceedings{DBLP:conf/iclr/ElskenMH19,
author = {Thomas Elsken and
Jan Hendrik Metzen and
Frank Hutter},
title = {Efficient Multi-Objective Neural Architecture Search via Lamarckian
Evolution},
publisher = {International Conference on Learning Representations},
year = {2019}
}
@inproceedings{DBLP:conf/iclr/BakerGNR17,
author = {Bowen Baker and
Otkrist Gupta and
Nikhil Naik and
Ramesh Raskar},
title = {Designing Neural Network Architectures using Reinforcement Learning},
publisher = {International Conference on Learning Representations},
year = {2017}
}
@inproceedings{DBLP:conf/cvpr/TanCPVSHL19,
author = {Mingxing Tan and
Bo Chen and
Ruoming Pang and
Vijay Vasudevan and
Mark Sandler and
Andrew Howard and
Quoc V. Le},
title = {MnasNet: Platform-Aware Neural Architecture Search for Mobile},
pages = {2820--2828},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2019}
}
@inproceedings{DBLP:conf/iclr/LiuSVFK18,
author = {Hanxiao Liu and
Karen Simonyan and
Oriol Vinyals and
Chrisantha Fernando and
Koray Kavukcuoglu},
title = {Hierarchical Representations for Efficient Architecture Search},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{DBLP:conf/iclr/CaiZH19,
author = {Han Cai and
Ligeng Zhu and
Song Han},
title = {ProxylessNAS: Direct Neural Architecture Search on Target Task and
Hardware},
publisher = {International Conference on Learning Representations},
year = {2019}
}
@inproceedings{DBLP:conf/cvpr/LiuCSAHY019,
author = {Chenxi Liu and
Liang-Chieh Chen and
Florian Schroff and
Hartwig Adam and
Wei Hua and
Alan L. Yuille and
Fei-Fei Li},
title = {Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic
Image Segmentation},
pages = {82--92},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2019}
}
@inproceedings{DBLP:conf/cvpr/WuDZWSWTVJK19,
author = {Bichen Wu and
Xiaoliang Dai and
Peizhao Zhang and
Yanghan Wang and
Fei Sun and
Yiming Wu and
Yuandong Tian and
Peter Vajda and
Yangqing Jia and
Kurt Keutzer},
title = {FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable
Neural Architecture Search},
pages = {10734--10742},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2019}
}
@inproceedings{DBLP:conf/iclr/XieZLL19,
author = {Sirui Xie and
Hehui Zheng and
Chunxiao Liu and
Liang Lin},
title = {{SNAS:} stochastic neural architecture search},
publisher = {International Conference on Learning Representations},
year = {2019}
}
@inproceedings{DBLP:conf/uai/LiT19,
author = {Liam Li and
Ameet Talwalkar},
title = {Random Search and Reproducibility for Neural Architecture Search},
pages = {129},
publisher = {Conference on Uncertainty in Artificial Intelligence},
year = {2019}
}
@inproceedings{DBLP:conf/cvpr/DongY19,
author = {Xuanyi Dong and
Yi Yang},
title = {Searching for a Robust Neural Architecture in Four {GPU} Hours},
pages = {1761--1770},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2019}
}
@inproceedings{DBLP:conf/iclr/XuX0CQ0X20,
author = {Yuhui Xu and
Lingxi Xie and
Xiaopeng Zhang and
Xin Chen and
Guo-Jun Qi and
Qi Tian and
Hongkai Xiong},
title = {{PC-DARTS:} Partial Channel Connections for Memory-Efficient Architecture
Search},
publisher = {International Conference on Learning Representations},
year = {2020}
}
@inproceedings{DBLP:conf/iclr/ZelaESMBH20,
author = {Arber Zela and
Thomas Elsken and
Tonmoy Saikia and
Yassine Marrakchi and
Thomas Brox and
Frank Hutter},
title = {Understanding and Robustifying Differentiable Architecture Search},
publisher = {International Conference on Learning Representations},
year = {2020}
}
@inproceedings{DBLP:conf/iclr/MeiLLJYYY20,
author = {Jieru Mei and
Yingwei Li and
Xiaochen Lian and
Xiaojie Jin and
Linjie Yang and
Alan L. Yuille and
Jianchao Yang},
title = {AtomNAS: Fine-Grained End-to-End Neural Architecture Search},
publisher = {International Conference on Learning Representations},
year = {2020}
}
@inproceedings{DBLP:journals/jmlr/LiJDRT17,
author = {Lisha Li and
Kevin G. Jamieson and
Giulia DeSalvo and
Afshin Rostamizadeh and
Ameet Talwalkar},
title = {Hyperband: {A} Novel Bandit-Based Approach to Hyperparameter Optimization},
publisher = {Journal of Machine Learning Research},
volume = {18},
pages = {185:1--185:52},
year = {2017}
}
@inproceedings{DBLP:conf/eccv/LiuZNSHLFYHM18,
author = {Chenxi Liu and
Barret Zoph and
Maxim Neumann and
Jonathon Shlens and
Wei Hua and
Li-Jia Li and
Li Fei-Fei and
Alan L. Yuille and
Jonathan Huang and
Kevin Murphy},
title = {Progressive Neural Architecture Search},
volume = {11205},
pages = {19--35},
publisher = {European Conference on Computer Vision},
year = {2018}
}
@inproceedings{DBLP:journals/taslp/FanTXQLL20,
author = {Yang Fan and
Fei Tian and
Yingce Xia and
Tao Qin and
Xiang-Yang Li and
Tie-Yan Liu},
title = {Searching Better Architectures for Neural Machine Translation},
publisher = {IEEE Transactions on Audio, Speech, and Language Processing},
volume = {28},
pages = {1574--1585},
year = {2020}
}
@inproceedings{DBLP:conf/ijcai/ChenLQWLDDHLZ20,
author = {Daoyuan Chen and
Yaliang Li and
Minghui Qiu and
Zhen Wang and
Bofang Li and
Bolin Ding and
Hongbo Deng and
Jun Huang and
Wei Lin and
Jingren Zhou},
title = {AdaBERT: Task-Adaptive {BERT} Compression with Differentiable Neural
Architecture Search},
publisher = {International Joint Conference on Artificial Intelligence},
pages = {2463--2469},
year = {2020}
}
@inproceedings{DBLP:conf/acl/WangWLCZGH20,
author = {Hanrui Wang and
Zhanghao Wu and
Zhijian Liu and
Han Cai and
Ligeng Zhu and
Chuang Gan and
Song Han},
title = {{HAT:} Hardware-Aware Transformers for Efficient Natural Language
Processing},
pages = {7675--7688},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/icml/CaiYZHY18,
author = {Han Cai and
Jiacheng Yang and
Weinan Zhang and
Song Han and
Yong Yu},
title = {Path-Level Network Transformation for Efficient Architecture Search},
volume = {80},
pages = {677--686},
publisher = {International Conference on Machine Learning},
year = {2018}
}
@inproceedings{DBLP:journals/corr/abs-2003-03384,
author = {Esteban Real and
Chen Liang and
David R. So and
Quoc V. Le},
title = {AutoML-Zero: Evolving Machine Learning Algorithms From Scratch},
publisher = {CoRR},
volume = {abs/2003.03384},
year = {2020}
}
@inproceedings{Chollet2017XceptionDL,
title={Xception: Deep Learning with Depthwise Separable Convolutions},
author = {Fran{\c{c}}ois Chollet},
publisher={IEEE Conference on Computer Vision and Pattern Recognition},
year={2017},
pages={1800-1807}
}
@inproceedings{DBLP:journals/tnn/AngelineSP94,
author = {Peter J. Angeline and
Gregory M. Saunders and
Jordan B. Pollack},
title = {An evolutionary algorithm that constructs recurrent neural networks},
publisher = {IEEE Transactions on Neural Networks},
volume = {5},
number = {1},
pages = {54--65},
year = {1994}
}
@inproceedings{stanley2002evolving,
title={Evolving neural networks through augmenting topologies},
author={Stanley, Kenneth O and Miikkulainen, Risto},
publisher={Evolutionary computation},
volume={10},
number={2},
pages={99--127},
year={2002}
}
@inproceedings{DBLP:journals/alife/StanleyDG09,
author = {Kenneth O. Stanley and
David B. D'Ambrosio and
Jason Gauci},
title = {A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks},
publisher = {Artificial Life},
volume = {15},
number = {2},
pages = {185--212},
year = {2009}
}
@inproceedings{DBLP:conf/ijcai/SuganumaSN18,
author = {Masanori Suganuma and
Shinichi Shirakawa and
Tomoharu Nagao},
title = {A Genetic Programming Approach to Designing Convolutional Neural Network
Architectures},
pages = {5369--5373},
publisher = {International Joint Conference on Artificial Intelligence},
year = {2018}
}
@inproceedings{DBLP:conf/iccv/XieY17,
author = {Lingxi Xie and
Alan L. Yuille},
title = {Genetic {CNN}},
pages = {1388--1397},
publisher = {IEEE International Conference on Computer Vision},
year = {2017}
}
@inproceedings{DBLP:conf/cvpr/ZhongYWSL18,
author = {Zhao Zhong and
Junjie Yan and
Wei Wu and
Jing Shao and
Cheng-Lin Liu},
title = {Practical Block-Wise Neural Network Architecture Generation},
pages = {2423--2432},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2018}
}
@inproceedings{DBLP:conf/icml/BergstraYC13,
author = {James Bergstra and
Daniel Yamins and
David D. Cox},
title = {Making a Science of Model Search: Hyperparameter Optimization in Hundreds
of Dimensions for Vision Architectures},
volume = {28},
pages = {115--123},
publisher = {International Conference on Machine Learning},
year = {2013}
}
@inproceedings{DBLP:conf/ijcai/DomhanSH15,
author = {Tobias Domhan and
Jost Tobias Springenberg and
Frank Hutter},
title = {Speeding Up Automatic Hyperparameter Optimization of Deep Neural Networks
by Extrapolation of Learning Curves},
pages = {3460--3468},
publisher = {International Joint Conference on Artificial Intelligence},
year = {2015}
}
@inproceedings{DBLP:conf/icml/MendozaKFSH16,
author = {Hector Mendoza and
Aaron Klein and
Matthias Feurer and
Jost Tobias Springenberg and
Frank Hutter},
title = {Towards Automatically-Tuned Neural Networks},
volume = {64},
pages = {58--65},
publisher = {International Conference on Machine Learning},
year = {2016}
}
@inproceedings{DBLP:journals/corr/abs-1807-06906,
author = {Arber Zela and
Aaron Klein and
Stefan Falkner and
Frank Hutter},
title = {Towards Automated Deep Learning: Efficient Joint Neural Architecture
and Hyperparameter Search},
publisher = {International Conference on Machine Learning},
year = {2018}
}
@inproceedings{li2020automated,
title={Automated and Lightweight Network Design via Random Search for Remote Sensing Image Scene Classification},
author={Li, Jihao and Diao, Wenhui and Sun, Xian and Feng, Yingchao and Zhang, Wenkai and Chang, Zhonghan and Fu, Kun},
publisher={The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences},
volume={43},
pages={1217--1224},
year={2020}
}
@inproceedings{DBLP:conf/cvpr/BenderLCCCKL20,
author = {Gabriel Bender and
Hanxiao Liu and
Bo Chen and
Grace Chu and
Shuyang Cheng and
Pieter-Jan Kindermans and
Quoc V. Le},
title = {Can Weight Sharing Outperform Random Architecture Search? An Investigation
With TuNAS},
pages = {14311--14320},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2020}
}
@inproceedings{DBLP:conf/aistats/KleinFBHH17,
author = {Aaron Klein and
Stefan Falkner and
Simon Bartels and
Philipp Hennig and
Frank Hutter},
title = {Fast Bayesian Optimization of Machine Learning Hyperparameters on
Large Datasets},
volume = {54},
pages = {528--536},
publisher = {International Conference on Artificial Intelligence and Statistics},
year = {2017}
}
@inproceedings{DBLP:journals/corr/ChrabaszczLH17,
author = {Patryk Chrabaszcz and
Ilya Loshchilov and
Frank Hutter},
title = {A Downsampled Variant of ImageNet as an Alternative to the {CIFAR}
datasets},
publisher = {CoRR},
volume = {abs/1707.08819},
year = {2017}
}
@inproceedings{DBLP:conf/aaai/CaiCZYW18,
author = {Han Cai and
Tianyao Chen and
Weinan Zhang and
Yong Yu and
Jun Wang},
title = {Efficient Architecture Search by Network Transformation},
pages = {2787--2794},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2018}
}
@inproceedings{DBLP:conf/iclr/ElskenMH18,
author = {Thomas Elsken and
Jan Hendrik Metzen and
Frank Hutter},
title = {Simple and efficient architecture search for Convolutional Neural
Networks},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{DBLP:conf/icml/BenderKZVL18,
author = {Gabriel Bender and
Pieter-Jan Kindermans and
Barret Zoph and
Vijay Vasudevan and
Quoc V. Le},
title = {Understanding and Simplifying One-Shot Architecture Search},
volume = {80},
pages = {549--558},
publisher = {International Conference on Machine Learning},
year = {2018}
}
@inproceedings{DBLP:conf/nips/SaxenaV16,
author = {Shreyas Saxena and
Jakob Verbeek},
title = {Convolutional Neural Fabrics},
publisher = {Advances in Neural Information Processing Systems},
pages = {4053--4061},
year = {2016}
}
@inproceedings{DBLP:conf/iclr/KleinFSH17,
author = {Aaron Klein and
Stefan Falkner and
Jost Tobias Springenberg and
Frank Hutter},
title = {Learning Curve Prediction with Bayesian Neural Networks},
publisher = {International Conference on Learning Representations},
year = {2017}
}
@inproceedings{DBLP:conf/iclr/BakerGRN18,
author = {Bowen Baker and
Otkrist Gupta and
Ramesh Raskar and
Nikhil Naik},
title = {Accelerating Neural Architecture Search using Performance Prediction},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{DBLP:conf/wmt/XiaTTGHCFGLLWWZ19,
author = {Yingce Xia and
Xu Tan and
Fei Tian and
Fei Gao and
Di He and
Weicong Chen and
Yang Fan and
Linyuan Gong and
Yichong Leng and
Renqian Luo and
Yiren Wang and
Lijun Wu and
Jinhua Zhu and
Tao Qin and
Tie-Yan Liu},
title = {Microsoft Research Asia's Systems for {WMT19}},
pages = {424--433},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/iclr/RamachandranZL18,
author = {Prajit Ramachandran and
Barret Zoph and
Quoc V. Le},
title = {Searching for Activation Functions},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{DBLP:journals/corr/abs-2009-02070,
author = {Wei Zhu and
Xiaoling Wang and
Xipeng Qiu and
Yuan Ni and
Guotong Xie},
title = {AutoTrans: Automating Transformer Design via Reinforced Architecture
Search},
publisher = {CoRR},
volume = {abs/2009.02070},
year = {2020}
}
@inproceedings{DBLP:conf/acl/WangWLCZGH20,
author = {Hanrui Wang and
Zhanghao Wu and
Zhijian Liu and
Han Cai and
Ligeng Zhu and
Chuang Gan and
Song Han},
title = {{HAT:} Hardware-Aware Transformers for Efficient Natural Language
Processing},
pages = {7675--7688},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-2008-06808,
author = {Henry Tsai and
Jayden Ooi and
Chun-Sung Ferng and
Hyung Won Chung and
Jason Riesa},
title = {Finding Fast Transformers: One-Shot Neural Architecture Search by
Component Composition},
publisher = {CoRR},
volume = {abs/2008.06808},
year = {2020}
}
@inproceedings{Wang2019ExploitingSC,
title={Exploiting Sentential Context for Neural Machine Translation},
author={Xing Wang and Zhaopeng Tu and Longyue Wang and Shuming Shi},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2019}
}
@inproceedings{Wei2020MultiscaleCD,
title={Multiscale Collaborative Deep Models for Neural Machine Translation},
author={Xiangpeng Wei and Heng Yu and Yue Hu and Yue Zhang and Rongxiang Weng and Weihua Luo},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2020}
}
@inproceedings{li2020shallow,
title={Shallow-to-Deep Training for Neural Machine Translation},
author={Li, Bei and Wang, Ziyang and Liu, Hui and Jiang, Yufan and Du, Quan and Xiao, Tong and Wang, Huizhen and Zhu, Jingbo},
publisher={Conference on Empirical Methods in Natural Language Processing},
year={2020}
}
@inproceedings{DBLP:journals/corr/abs-2007-06257,
author = {Hongfei Xu and
Qiuhui Liu and
Deyi Xiong and
Josef van Genabith},
title = {Transformer with Depth-Wise {LSTM}},
publisher = {CoRR},
volume = {abs/2007.06257},
year = {2020}
}
@inproceedings{DBLP:conf/acl/XuLGXZ20,
author = {Hongfei Xu and
Qiuhui Liu and
Josef van Genabith and
Deyi Xiong and
Jingyi Zhang},
title = {Lipschitz Constrained Parameter Initialization for Deep Transformers},
pages = {397--402},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-2006-10369,
author = {Jungo Kasai and
Nikolaos Pappas and
Hao Peng and
James Cross and
Noah A. Smith},
title = {Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff
in Machine Translation},
publisher = {CoRR},
volume = {abs/2006.10369},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-1806-01261,
author = {Peter W. Battaglia and
Jessica B. Hamrick and
Victor Bapst and
Alvaro Sanchez-Gonzalez and
Vin{\'{\i}}cius Flores Zambaldi and
Mateusz Malinowski and
Andrea Tacchetti and
David Raposo and
Adam Santoro and
Ryan Faulkner and
{\c{C}}aglar G{\"{u}}l{\c{c}}ehre and
H. Francis Song and
Andrew J. Ballard and
Justin Gilmer and
George E. Dahl and
Ashish Vaswani and
Kelsey R. Allen and
Charles Nash and
Victoria Langston and
Chris Dyer and
Nicolas Heess and
Daan Wierstra and
Pushmeet Kohli and
Matthew Botvinick and
Oriol Vinyals and
Yujia Li and
Razvan Pascanu},
title = {Relational inductive biases, deep learning, and graph networks},
publisher = {CoRR},
volume = {abs/1806.01261},
year = {2018}
}
@inproceedings{Shaw2018SelfAttentionWR,
author = {Peter Shaw and
Jakob Uszkoreit and
Ashish Vaswani},
title = {Self-Attention with Relative Position Representations},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
pages = {464--468},
year = {2018},
}
@inproceedings{Dai2019TransformerXLAL,
author = {Zihang Dai and
Zhilin Yang and
Yiming Yang and
Jaime G. Carbonell and
Quoc V. Le and
Ruslan Salakhutdinov},
title = {Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {2978--2988},
year = {2019}
}
@inproceedings{vaswani2017attention,
title={Attention is All You Need},
author={Ashish {Vaswani} and Noam {Shazeer} and Niki {Parmar} and Jakob {Uszkoreit} and Llion {Jones} and Aidan N. {Gomez} and Lukasz {Kaiser} and Illia {Polosukhin}},
publisher={International Conference on Neural Information Processing},
pages={5998--6008},
year={2017}
}
@inproceedings{DBLP:conf/acl/LiXTZZZ17,
author = {Junhui Li and
Deyi Xiong and
Zhaopeng Tu and
Muhua Zhu and
Min Zhang and
Guodong Zhou},
title = {Modeling Source Syntax for Neural Machine Translation},
pages = {688--697},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/acl/EriguchiHT16,
author = {Akiko Eriguchi and
Kazuma Hashimoto and
Yoshimasa Tsuruoka},
title = {Tree-to-Sequence Attentional Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{Yang2017TowardsBH,
author = {Baosong Yang and
Derek F. Wong and
Tong Xiao and
Lidia S. Chao and
Jingbo Zhu},
title = {Towards Bidirectional Hierarchical Representations for Attention-based
Neural Machine Translation},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {1432--1441},
year = {2017}
}
@inproceedings{DBLP:conf/acl/ChenHCC17,
author = {Huadong Chen and
Shujian Huang and
David Chiang and
Jiajun Chen},
title = {Improved Neural Machine Translation with a Syntax-Aware Encoder and
Decoder},
pages = {1936--1945},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{TuModeling,
author = {Zhaopeng Tu and
Zhengdong Lu and
Yang Liu and
Xiaohua Liu and
Hang Li},
title = {Modeling Coverage for Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/wmt/SennrichH16,
author = {Rico Sennrich and
Barry Haddow},
title = {Linguistic Input Features Improve Neural Machine Translation},
pages = {83--91},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/emnlp/ShiPK16,
author = {Xing Shi and
Inkit Padhi and
Kevin Knight},
title = {Does String-Based Neural {MT} Learn Source Syntax?},
pages = {1526--1534},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/acl/BugliarelloO20,
author = {Emanuele Bugliarello and
Naoaki Okazaki},
title = {Enhancing Machine Translation with Dependency-Aware Self-Attention},
pages = {1618--1627},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{Aharoni2017TowardsSN,
title={Towards String-To-Tree Neural Machine Translation},
author={Roee Aharoni and
Yoav Goldberg},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2017}
}
@inproceedings{DBLP:conf/iclr/Alvarez-MelisJ17,
author = {David Alvarez-Melis and
Tommi S. Jaakkola},
title = {Tree-structured decoding with doubly-recurrent neural networks},
publisher = {International Conference on Learning Representations},
year = {2017}
}
@inproceedings{DBLP:conf/naacl/DyerKBS16,
author = {Chris Dyer and
Adhiguna Kuncoro and
Miguel Ballesteros and
Noah A. Smith},
title = {Recurrent Neural Network Grammars},
pages = {199--209},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@book{aho1972theory,
author = {Aho, Alfred V and
Ullman, Jeffrey D},
title = {The theory of parsing, translation, and compiling},
publisher = {Prentice-Hall Englewood Cliffs, NJ},
year = {1973},
}
@inproceedings{DBLP:journals/corr/LuongLSVK15,
author = {Minh-Thang Luong and
Quoc V. Le and
Ilya Sutskever and
Oriol Vinyals and
Lukasz Kaiser},
title = {Multi-task Sequence to Sequence Learning},
publisher = {International Conference on Learning Representations},
year = {2016}
}
@inproceedings{DBLP:conf/wmt/NadejdeRSDJKB17,
author = {Maria Nadejde and
Siva Reddy and
Rico Sennrich and
Tomasz Dwojak and
Marcin Junczys-Dowmunt and
Philipp Koehn and
Alexandra Birch},
title = {Predicting Target Language {CCG} Supertags Improves Neural Machine
Translation},
pages = {68--79},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/acl/WuZYLZ17,
author = {Shuangzhi Wu and
Dongdong Zhang and
Nan Yang and
Mu Li and
Ming Zhou},
title = {Sequence-to-Dependency Neural Machine Translation},
pages = {698--707},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:journals/corr/abs-1808-09374,
author = {Xinyi Wang and
Hieu Pham and
Pengcheng Yin and
Graham Neubig},
title = {A Tree-based Decoder for Neural Machine Translation},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {4772--4777},
year = {2018}
}
@inproceedings{Tong2016Syntactic,
author = {Tong Xiao and
Jingbo Zhu and
Chunliang Zhang and
Tongran Liu},
title = {Syntactic Skeleton-Based Translation},
pages = {2856--2862},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2016},
}
@inproceedings{DBLP:conf/emnlp/WangTWS19a,
author = {Xing Wang and
Zhaopeng Tu and
Longyue Wang and
Shuming Shi},
title = {Self-Attention with Structural Position Representations},
pages = {1403--1409},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{Liu2020LearningTE,
title={Learning to Encode Position for Transformer with Continuous Dynamical Model},
author={Xuanqing Liu and Hsiang-Fu Yu and Inderjit Dhillon and Cho-Jui Hsieh},
publisher={ArXiv},
year={2020},
volume={abs/2003.09229}
}
@inproceedings{DBLP:conf/nips/ChenRBD18,
author = {Tian Qi Chen and
Yulia Rubanova and
Jesse Bettencourt and
David Duvenaud},
title = {Neural Ordinary Differential Equations},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {6572--6583},
year = {2018}
}
@inproceedings{DBLP:journals/corr/LuongPM15,
author = {Thang Luong and
Hieu Pham and
Christopher D. Manning},
title = {Effective Approaches to Attention-based Neural Machine Translation},
publisher = {Conference on Empirical Methods in Natural Language Processing},
pages = {1412--1421},
year = {2015}
}
@inproceedings{Yang2018ModelingLF,
author = {Baosong Yang and
Zhaopeng Tu and
Derek F. Wong and
Fandong Meng and
Lidia S. Chao and
Tong Zhang},
title = {Modeling Localness for Self-Attention Networks},
pages = {4449--4458},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/aaai/GuoQLXZ20,
author = {Qipeng Guo and
Xipeng Qiu and
Pengfei Liu and
Xiangyang Xue and
Zheng Zhang},
title = {Multi-Scale Self-Attention for Text Classification},
pages = {7847--7854},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2020}
}
@inproceedings{Wu2019PayLA,
author = {Felix Wu and
Angela Fan and
Alexei Baevski and
Yann N. Dauphin and
Michael Auli},
title = {Pay Less Attention with Lightweight and Dynamic Convolutions},
publisher = {International Conference on Learning Representations},
year = {2019},
}
@inproceedings{DBLP:conf/interspeech/GulatiQCPZYHWZW20,
author = {Anmol Gulati and
James Qin and
Chung-Cheng Chiu and
Niki Parmar and
Yu Zhang and
Jiahui Yu and
Wei Han and
Shibo Wang and
Zhengdong Zhang and
Yonghui Wu and
Ruoming Pang},
title = {Conformer: Convolution-augmented Transformer for Speech Recognition},
pages = {5036--5040},
publisher = {International Speech Communication Association},
year = {2020}
}
@inproceedings{DBLP:conf/cvpr/XieGDTH17,
author = {Saining Xie and
Ross B. Girshick and
Piotr Doll{\'{a}}r and
Zhuowen Tu and
Kaiming He},
title = {Aggregated Residual Transformations for Deep Neural Networks},
pages = {5987--5995},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2017}
}
@inproceedings{DBLP:journals/corr/abs-1711-02132,
author = {Karim Ahmed and
Nitish Shirish Keskar and
Richard Socher},
title = {Weighted Transformer Network for Machine Translation},
publisher = {CoRR},
volume = {abs/1711.02132},
year = {2017}
}
@inproceedings{DBLP:journals/corr/abs-2006-10270,
author = {Yang Fan and
Shufang Xie and
Yingce Xia and
Lijun Wu and
Tao Qin and
Xiang-Yang Li and
Tie-Yan Liu},
title = {Multi-branch Attentive Transformer},
publisher = {CoRR},
volume = {abs/2006.10270},
year = {2020}
}
@inproceedings{DBLP:conf/emnlp/YanMZ20,
author = {Jianhao Yan and
Fandong Meng and
Jie Zhou},
title = {Multi-Unit Transformers for Neural Machine Translation},
pages = {1047--1059},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2020}
}
@inproceedings{李北2019面向神经机器翻译的集成学习方法分析,
title={面向神经机器翻译的集成学习方法分析},
author={李北 and 王强 and 肖桐 and 姜雨帆 and 张哲旸 and 刘继强 and 张俐 and 于清},
publisher={中文信息学报},
volume={33},
number={3},
year={2019},
}
@inproceedings{DBLP:conf/iclr/WuLLLH20,
author = {Zhanghao Wu and
Zhijian Liu and
Ji Lin and
Yujun Lin and
Song Han},
title = {Lite Transformer with Long-Short Range Attention},
publisher = {International Conference on Learning Representations},
year = {2020}
}
@inproceedings{DBLP:conf/iclr/DehghaniGVUK19,
author = {Mostafa Dehghani and
Stephan Gouws and
Oriol Vinyals and
Jakob Uszkoreit and
Lukasz Kaiser},
title = {Universal Transformers},
publisher = {International Conference on Learning Representations},
year = {2019}
}
@inproceedings{Lan2020ALBERTAL,
title={ALBERT: A Lite BERT for Self-supervised Learning of Language Representations},
author={Zhenzhong Lan and Mingda Chen and Sebastian Goodman and Kevin Gimpel and Piyush Sharma and Radu Soricut},
publisher={International Conference on Learning Representations},
year={2020}
}
@inproceedings{DBLP:conf/naacl/HaoWYWZT19,
author = {Jie Hao and
Xing Wang and
Baosong Yang and
Longyue Wang and
Jinfeng Zhang and
Zhaopeng Tu},
title = {Modeling Recurrence for Transformer},
pages = {1198--1207},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/QiuMLYW020,
author = {Jiezhong Qiu and
Hao Ma and
Omer Levy and
Wen-tau Yih and
Sinong Wang and
Jie Tang},
title = {Blockwise Self-Attention for Long Document Understanding},
pages = {2555--2565},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2020}
}
@inproceedings{DBLP:conf/iclr/LiuSPGSKS18,
author = {Peter J. Liu and
Mohammad Saleh and
Etienne Pot and
Ben Goodrich and
Ryan Sepassi and
Lukasz Kaiser and
Noam Shazeer},
title = {Generating Wikipedia by Summarizing Long Sequences},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{DBLP:journals/corr/abs-2004-05150,
author = {Iz Beltagy and
Matthew Peters and
Arman Cohan},
title = {Longformer: The Long-Document Transformer},
publisher = {CoRR},
volume = {abs/2004.05150},
year = {2020}
}
@inproceedings{Kitaev2020ReformerTE,
author = {Nikita Kitaev and
Lukasz Kaiser and
Anselm Levskaya},
title = {Reformer: The Efficient Transformer},
publisher = {International Conference on Learning Representations},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-2003-05997,
author = {Aurko Roy and
Mohammad Saffar and
Ashish Vaswani and
David Grangier},
title = {Efficient Content-Based Sparse Attention with Routing Transformers},
publisher = {CoRR},
volume = {abs/2003.05997},
year = {2020}
}
@inproceedings{Katharopoulos2020TransformersAR,
title={Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention},
author={Angelos Katharopoulos and Apoorv Vyas and Nikolaos Pappas and Franccois Fleuret},
publisher={CoRR},
year={2020},
volume={abs/2006.16236}
}
@inproceedings{DBLP:journals/corr/abs-2009-14794,
author = {Krzysztof Choromanski and
Valerii Likhosherstov and
David Dohan and
Xingyou Song and
Andreea Gane and
Tam{\'{a}}s Sarl{\'{o}}s and
Peter Hawkins and
Jared Davis and
Afroz Mohiuddin and
Lukasz Kaiser and
David Belanger and
Lucy Colwell and
Adrian Weller},
title = {Rethinking Attention with Performers},
publisher = {CoRR},
volume = {abs/2009.14794},
year = {2020}
}
@inproceedings{DBLP:conf/emnlp/HaoWSZT19,
author = {Jie Hao and
Xing Wang and
Shuming Shi and
Jinfeng Zhang and
Zhaopeng Tu},
title = {Multi-Granularity Self-Attention for Neural Machine Translation},
pages = {887--897},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/Lin0RLS18,
author = {Junyang Lin and
Xu Sun and
Xuancheng Ren and
Muyu Li and
Qi Su},
title = {Learning When to Concentrate or Divert Attention: Self-Adaptive Attention
Temperature for Neural Machine Translation},
pages = {2985--2990},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:journals/corr/abs-2006-04768,
author = {Sinong Wang and
Belinda Z. Li and
Madian Khabsa and
Han Fang and
Hao Ma},
title = {Linformer: Self-Attention with Linear Complexity},
publisher = {CoRR},
volume = {abs/2006.04768},
year = {2020}
}
@inproceedings{DBLP:conf/nips/BergstraBBK11,
author = {James Bergstra and
R{\'{e}}mi Bardenet and
Yoshua Bengio and
Bal{\'{a}}zs K{\'{e}}gl},
title = {Algorithms for Hyper-Parameter Optimization},
publisher = {Advances in Neural Information Processing Systems},
pages = {2546--2554},
year = {2011}
}
@inproceedings{DBLP:conf/lion/HutterHL11,
author = {Frank Hutter and
Holger H. Hoos and
Kevin Leyton-Brown},
title = {Sequential Model-Based Optimization for General Algorithm Configuration},
series = {Lecture Notes in Computer Science},
volume = {6683},
pages = {507--523},
publisher = {Learning and Intelligent Optimization},
year = {2011}
}
@inproceedings{DBLP:conf/icml/BergstraYC13,
author = {James Bergstra and
Daniel Yamins and
David D. Cox},
title = {Making a Science of Model Search: Hyperparameter Optimization in Hundreds
of Dimensions for Vision Architectures},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {28},
pages = {115--123},
publisher = {International Conference on Machine Learning},
year = {2013}
}
@inproceedings{DBLP:conf/iccv/ChenXW019,
author = {Xin Chen and
Lingxi Xie and
Jun Wu and
Qi Tian},
title = {Progressive Differentiable Architecture Search: Bridging the Depth
Gap Between Search and Evaluation},
pages = {1294--1303},
publisher = {IEEE International Conference on Computer Vision},
year = {2019}
}
@inproceedings{DBLP:conf/icml/ChenH20,
author = {Xiangning Chen and
Cho-Jui Hsieh},
title = {Stabilizing Differentiable Architecture Search via Perturbation-based
Regularization},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {1554--1565},
publisher = {International Conference on Machine Learning},
year = {2020}
}
@inproceedings{Jawahar2019WhatDB,
title={What Does BERT Learn about the Structure of Language?},
author={Ganesh Jawahar and Beno{\^{\i}}t Sagot and Djam{\'e} Seddah},
publisher={Annual Meeting of the Association for Computational Linguistics},
year={2019}
}
@inproceedings{DBLP:conf/emnlp/Ethayarajh19,
author = {Kawin Ethayarajh},
title = {How Contextual are Contextualized Word Representations? Comparing
the Geometry of BERT, ELMo, and {GPT-2} Embeddings},
pages = {55--65},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-1905-09418,
author = {Elena Voita and
David Talbot and
Fedor Moiseev and
Rico Sennrich and
Ivan Titov},
title = {Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy
Lifting, the Rest Can Be Pruned},
pages = {5797--5808},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019},
}
@inproceedings{Michel2019AreSH,
title={Are Sixteen Heads Really Better than One?},
author = {Paul Michel and
Omer Levy and
Graham Neubig},
title = {Are Sixteen Heads Really Better than One?},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {14014--14024},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/LiTYLZ18,
author = {Jian Li and
Zhaopeng Tu and
Baosong Yang and
Michael R. Lyu and
Tong Zhang},
title = {Multi-Head Attention with Disagreement Regularization},
pages = {2897--2903},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{Su2018VariationalRN,
title={Variational Recurrent Neural Machine Translation},
author={Jinsong Su and Shan Wu and Deyi Xiong and Yaojie Lu and Xianpei Han and Biao Zhang},
publisher={AAAI Conference on Artificial Intelligence},
pages={5488--5495},
year={2018}
}
@inproceedings{DBLP:conf/acl/SetiawanSNP20,
author = {Hendra Setiawan and
Matthias Sperber and
Udhyakumar Nallasamy and
Matthias Paulik},
title = {Variational Neural Machine Translation with Normalizing Flows},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{Li2020NeuralMT,
author = {Yanyang Li and
Qiang Wang and
Tong Xiao and
Tongran Liu and
Jingbo Zhu},
title = {Neural Machine Translation with Joint Representation},
pages = {8285--8292},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2020}
}
@inproceedings{JMLR:v15:srivastava14a,
author = {Nitish Srivastava and Geoffrey Hinton and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov},
title = {Dropout: A Simple Way to Prevent Neural Networks from Overfitting},
publisher = {Journal of Machine Learning Research},
year = {2014},
volume = {15},
pages = {1929-1958},
}
@inproceedings{Szegedy_2016_CVPR,
author = {Christian Szegedy and
Vincent Vanhoucke and
Sergey Ioffe and
Jonathon Shlens and
Zbigniew Wojna},
title = {Rethinking the Inception Architecture for Computer Vision},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
pages = {2818--2826},
year = {2016},
}
@inproceedings{Chen2018TheBO,
author = {Mia Xu Chen and
Orhan Firat and
Ankur Bapna and
Melvin Johnson and
Wolfgang Macherey and
George F. Foster and
Llion Jones and
Mike Schuster and
Noam Shazeer and
Niki Parmar and
Ashish Vaswani and
Jakob Uszkoreit and
Lukasz Kaiser and
Zhifeng Chen and
Yonghui Wu and
Macduff Hughes},
title = {The Best of Both Worlds: Combining Recent Advances in Neural Machine
Translation},
pages = {76--86},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
%%%%% chapter 15------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 16------------------------------------------------------
@inproceedings{DBLP:conf/wmt/CurreyBH17,
author = {Anna Currey and
Antonio Valerio Miceli Barone and
Kenneth Heafield},
title = {Copied Monolingual Data Improves Low-Resource Neural Machine Translation},
pages = {148--156},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/EdunovOAG18,
author = {Sergey Edunov and
Myle Ott and
Michael Auli and
David Grangier},
title = {Understanding Back-Translation at Scale},
pages = {489--500},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/FadaeeM18,
author = {Marzieh Fadaee and
Christof Monz},
title = {Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation},
pages = {436--446},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/nlpcc/XuLXLLXZ19,
author = {Nuo Xu and
Yinqiao Li and
Chen Xu and
Yanyang Li and
Bei Li and
Tong Xiao and
Jingbo Zhu},
title = {Analysis of Back-Translation Methods for Low-Resource Neural Machine
Translation},
volume = {11839},
pages = {466--475},
publisher = {Natural Language Processing and Chinese Computing},
year = {2019}
}
@inproceedings{DBLP:conf/wmt/CaswellCG19,
author = {Isaac Caswell and
Ciprian Chelba and
David Grangier},
title = {Tagged Back-Translation},
pages = {53--63},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/WangLWLS19,
author = {Shuo Wang and
Yang Liu and
Chao Wang and
Huanbo Luan and
Maosong Sun},
title = {Improving Back-Translation with Uncertainty-based Confidence Estimation},
pages = {791--802},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs200111327,
author = {Idris Abdulmumin and
Bashir Shehu Galadanci and
Abubakar Isa},
title = {Iterative Batch Back-Translation for Neural Machine Translation: {A}
Conceptual Model},
publisher = {CoRR},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs200403672,
author = {Zi-Yi Dou and
Antonios Anastasopoulos and
Graham Neubig},
title = {Dynamic Data Selection and Weighting for Iterative Back-Translation},
pages = {5894--5904},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2020}
}
@inproceedings{DBLP:conf/emnlp/WuZHGQLL19,
author = {Lijun Wu and
Jinhua Zhu and
Di He and
Fei Gao and
Tao Qin and
Jianhuang Lai and
Tie-Yan Liu},
title = {Machine Translation With Weakly Paired Documents},
pages = {4374--4383},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-1901-09069,
author = {Felipe Almeida and
Geraldo Xex{\'{e}}o},
title = {Word Embeddings: {A} Survey},
publisher = {CoRR},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-2002-06823,
author = {Jinhua Zhu and
Yingce Xia and
Lijun Wu and
Di He and
Tao Qin and
Wengang Zhou and
Houqiang Li and
Tie-Yan Liu},
title = {Incorporating {BERT} into Neural Machine Translation},
publisher = {International Conference on Learning Representations},
year = {2020}
}
@inproceedings{song2019mass,
author = {Kaitao Song and
Xu Tan and
Tao Qin and
Jianfeng Lu and
Tie-Yan Liu},
title = {{MASS:} Masked Sequence to Sequence Pre-training for Language Generation},
volume = {97},
pages = {5926--5936},
publisher = {International Conference on Machine Learning},
year = {2019}
}
@inproceedings{DBLP:journals/corr/Ruder17a,
author = {Sebastian Ruder},
title = {An Overview of Multi-Task Learning in Deep Neural Networks},
publisher = {CoRR},
volume = {abs/1706.05098},
year = {2017}
}
@inproceedings{DBLP:conf/icml/XiaQCBYL17,
author = {Yingce Xia and
Tao Qin and
Wei Chen and
Jiang Bian and
Nenghai Yu and
Tie-Yan Liu},
title = {Dual Supervised Learning},
volume = {70},
pages = {3789--3798},
publisher = {International Conference on Machine Learning},
year = {2017}
}
@inproceedings{DBLP:conf/nips/HeXQWYLM16,
author = {Di He and
Yingce Xia and
Tao Qin and
Liwei Wang and
Nenghai Yu and
Tie-Yan Liu and
Wei-Ying Ma},
title = {Dual Learning for Machine Translation},
pages = {820--828},
year = {2016}
}
@inproceedings{DBLP:conf/nips/SuttonMSM99,
author = {Richard Sutton and
David Allen McAllester and
Satinder Singh and
Yishay Mansour},
title = {Policy Gradient Methods for Reinforcement Learning with Function Approximation},
pages = {1057--1063},
publisher = {The {MIT} Press},
year = {1999}
}
@inproceedings{DBLP:conf/aclnmt/HoangKHC18,
author = {Cong Duy Vu Hoang and
Philipp Koehn and
Gholamreza Haffari and
Trevor Cohn},
title = {Iterative Back-Translation for Neural Machine Translation},
pages = {18--24},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/icml/OttAGR18,
author = {Myle Ott and
Michael Auli and
David Grangier and
Marc'Aurelio Ranzato},
title = {Analyzing Uncertainty in Neural Machine Translation},
volume = {80},
pages = {3953--3962},
publisher = {International Conference on Machine Learning},
year = {2018}
}
@inproceedings{finding2006adafre,
author = {Sisay Fissaha Adafre and Maarten de Rijke},
title = {Finding Similar Sentences across Multiple Languages in Wikipedia},
publisher = {Annual Conference of the European Association for Machine Translation},
year = {2006}
}
@inproceedings{method2008keiji,
author = {Keiji Yasuda and Eiichiro Sumita},
title = {Method for building sentence-aligned corpus from wikipedia},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2008}
}
@inproceedings{DBLP:journals/coling/MunteanuM05,
author = {Dragos Stefan Munteanu and
Daniel Marcu},
title = {Improving Machine Translation Performance by Exploiting Non-Parallel
Corpora},
publisher = {Computational Linguistics},
volume = {31},
number = {4},
pages = {477--504},
year = {2005}
}
@inproceedings{DBLP:conf/acl/XiaKAN19,
author = {Mengzhou Xia and
Xiang Kong and
Antonios Anastasopoulos and
Graham Neubig},
title = {Generalized Data Augmentation for Low-Resource Translation},
pages = {5786--5796},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/GaoZWXQCZL19,
author = {Fei Gao and
Jinhua Zhu and
Lijun Wu and
Yingce Xia and
Tao Qin and
Xueqi Cheng and
Wengang Zhou and
Tie-Yan Liu},
title = {Soft Contextual Data Augmentation for Neural Machine Translation},
pages = {5539--5544},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/WuWXQLL19,
author = {Lijun Wu and
Yiren Wang and
Yingce Xia and
Tao Qin and
Jianhuang Lai and
Tie-Yan Liu},
title = {Exploiting Monolingual Data at Scale for Neural Machine Translation},
pages = {4205--4215},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/LiLHZZ19,
author = {Guanlin Li and
Lemao Liu and
Guoping Huang and
Conghui Zhu and
Tiejun Zhao},
title = {Understanding Data Augmentation in Neural Machine Translation: Two
Perspectives towards Generalization},
pages = {5688--5694},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{2015OnGulcehre,
title = {On Using Monolingual Corpora in Neural Machine Translation},
author = {Gulcehre Caglar and
Firat Orhan and
Xu Kelvin and
Cho Kyunghyun and
Barrault Loic and
Lin Huei Chi and
Bougares Fethi and
Schwenk Holger and
Bengio Yoshua},
publisher = {Computer Science},
year = {2015},
}
@inproceedings{黄书剑0统计机器翻译中的词对齐研究,
title={统计机器翻译中的词对齐研究},
author={黄书剑},
publisher={南京大学},
year={2012}
}
@inproceedings{DBLP:journals/corr/MikolovLS13,
author = {Tomas Mikolov and
Quoc V. Le and
Ilya Sutskever},
title = {Exploiting Similarities among Languages for Machine Translation},
publisher = {CoRR},
volume = {abs/1309.4168},
year = {2013}
}
@inproceedings{DBLP:conf/acl/VulicK16,
author = {Ivan Vulic and
Anna Korhonen},
title = {On the Role of Seed Lexicons in Learning Bilingual Word Embeddings},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/acl/ArtetxeLA17,
author = {Mikel Artetxe and
Gorka Labaka and
Eneko Agirre},
title = {Learning bilingual word embeddings with (almost) no bilingual data},
pages = {451--462},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{1966ASchnemann,
title={A generalized solution of the orthogonal procrustes problem},
author={Schnemann and Peter},
publisher={Psychometrika},
volume={31},
number={1},
pages={1-10},
year={1966},
}
@inproceedings{DBLP:conf/iclr/LampleCRDJ18,
author = {Guillaume Lample and
Alexis Conneau and
Marc'Aurelio Ranzato and
Ludovic Denoyer and
Herv{\'{e}} J{\'{e}}gou},
title = {Word translation without parallel data},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{DBLP:conf/acl/ZhangLLS17,
author = {Meng Zhang and
Yang Liu and
Huanbo Luan and
Maosong Sun},
title = {Adversarial Training for Unsupervised Bilingual Lexicon Induction},
pages = {1959--1970},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/Alvarez-MelisJ18,
author = {David Alvarez-Melis and
Tommi S. Jaakkola},
title = {Gromov-Wasserstein Alignment of Word Embedding Spaces},
pages = {1881--1890},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/lrec/GarneauGBDL20,
author = {Nicolas Garneau and
Mathieu Godbout and
David Beauchemin and
Audrey Durand and
Luc Lamontagne},
title = {A Robust Self-Learning Method for Fully Unsupervised Cross-Lingual
Mappings of Word Embeddings: Making the Method Robustly Reproducible
as Well},
pages = {5546--5554},
publisher = {Language Resources and Evaluation Conference},
year = {2020}
}
@inproceedings{DBLP:conf/naacl/XingWLL15,
author = {Chao Xing and
Dong Wang and
Chao Liu and
Yiye Lin},
title = {Normalized Word Embedding and Orthogonal Transform for Bilingual Word
Translation},
pages = {1006--1011},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:conf/iclr/SmithTHH17,
author = {Samuel L. Smith and
David H. P. Turban and
Steven Hamblin and
Nils Y. Hammerla},
title = {Offline bilingual word vectors, orthogonal transformations and the
inverted softmax},
publisher = {International Conference on Learning Representations},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/VulicGRK19,
author = {Ivan Vulic and
Goran Glavas and
Roi Reichart and
Anna Korhonen},
title = {Do We Really Need Fully Unsupervised Cross-Lingual Embeddings?},
pages = {4406--4417},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:journals/talip/MarieF20,
author = {Benjamin Marie and
Atsushi Fujita},
title = {Iterative Training of Unsupervised Neural and Statistical Machine
Translation Systems},
publisher = {ACM Transactions on Asian and Low-Resource Language Information Processing},
volume = {19},
number = {5},
pages = {68:1--68:21},
year = {2020}
}
@inproceedings{DBLP:conf/acl/ArtetxeLA19,
author = {Mikel Artetxe and
Gorka Labaka and
Eneko Agirre},
title = {An Effective Approach to Unsupervised Machine Translation},
pages = {194--203},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/PourdamghaniAGK19,
author = {Nima Pourdamghani and
Nada Aldarrab and
Marjan Ghazvininejad and
Kevin Knight and
Jonathan May},
title = {Translating Translationese: {A} Two-Step Approach to Unsupervised
Machine Translation},
pages = {3057--3062},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/nips/ConneauL19,
author = {Alexis Conneau and
Guillaume Lample},
title = {Cross-lingual Language Model Pretraining},
pages = {7057--7067},
publisher = {Annual Conference on Neural Information Processing Systems},
year = {2019}
}
@inproceedings{DBLP:journals/ipm/FarhanTAJATT20,
author = {Wael Farhan and
Bashar Talafha and
Analle Abuammar and
Ruba Jaikat and
Mahmoud Al-Ayyoub and
Ahmad Bisher Tarakji and
Anas Toma},
title = {Unsupervised dialectal neural machine translation},
publisher = {Information Processing \& Management},
volume = {57},
number = {3},
pages = {102181},
year = {2020}
}
@inproceedings{A2020Li,
title={A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction},
author={Yanyang Li and Yingfeng Luo and Ye Lin and Quan Du and Huizhen Wang and Shujian Huang and Tong Xiao and Jingbo Zhu},
publisher={International Conference on Computational Linguistics},
year={2020}
}
@inproceedings{2018When,
title={When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation?},
author={ Qi, Ye and Sachan, Devendra Singh and Felix, Matthieu and Padmanabhan, Sarguna Janani and Neubig, Graham },
publisher={Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year={2018},
}
@inproceedings{DBLP:conf/emnlp/ClinchantJN19,
author = {St{\'{e}}phane Clinchant and
Kweon Woo Jung and
Vassilina Nikoulina},
title = {On the use of {BERT} for Neural Machine Translation},
pages = {108--117},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/aaai/YangW0Z00020,
author = {Jiacheng Yang and
Mingxuan Wang and
Hao Zhou and
Chengqi Zhao and
Weinan Zhang and
Yong Yu and
Lei Li},
title = {Towards Making the Most of {BERT} in Neural Machine Translation},
pages = {9378--9385},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2020}
}
@inproceedings{DBLP:conf/aaai/WengYHCL20,
author = {Rongxiang Weng and
Heng Yu and
Shujian Huang and
Shanbo Cheng and
Weihua Luo},
title = {Acquiring Knowledge from Pre-Trained Model to Neural Machine Translation},
pages = {9266--9273},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-2001-08210,
author = {Yinhan Liu and
Jiatao Gu and
Naman Goyal and
Xian Li and
Sergey Edunov and
Marjan Ghazvininejad and
Mike Lewis and
Luke Zettlemoyer},
title = {Multilingual Denoising Pre-training for Neural Machine Translation},
publisher = {Transactions of the Association for Computational Linguistics},
volume = {8},
pages = {726--742},
year = {2020}
}
@inproceedings{DBLP:conf/aaai/JiZDZCL20,
author = {Baijun Ji and
Zhirui Zhang and
Xiangyu Duan and
Min Zhang and
Boxing Chen and
Weihua Luo},
title = {Cross-Lingual Pre-Training Based Transfer for Zero-Shot Neural Machine
Translation},
pages = {115--122},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2020}
}
@inproceedings{DBLP:conf/acl/LewisLGGMLSZ20,
author = {Mike Lewis and
Yinhan Liu and
Naman Goyal and
Marjan Ghazvininejad and
Abdelrahman Mohamed and
Omer Levy and
Veselin Stoyanov and
Luke Zettlemoyer},
title = {{BART:} Denoising Sequence-to-Sequence Pre-training for Natural Language
Generation, Translation, and Comprehension},
pages = {7871--7880},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-2009-08088,
author = {Zhen Yang and
Bojie Hu and
Ambyera Han and
Shen Huang and
Qi Ju},
title = {{CSP:} Code-Switching Pre-training for Neural Machine Translation},
pages = {2624--2636},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-2010-09403,
author = {Dusan Varis and
Ondrej Bojar},
title = {Unsupervised Pretraining for Neural Machine Translation Using Elastic
Weight Consolidation},
pages = {130--135},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/LampleOCDR18,
author = {Guillaume Lample and
Myle Ott and
Alexis Conneau and
Ludovic Denoyer and
Marc'Aurelio Ranzato},
title = {Phrase-Based {\&} Neural Unsupervised Machine Translation},
pages = {5039--5049},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:journals/jbd/ShortenK19,
author = {Connor Shorten and
Taghi M. Khoshgoftaar},
title = {A survey on Image Data Augmentation for Deep Learning},
publisher = {Journal of Big Data},
volume = {6},
pages = {60},
year = {2019}
}
@inproceedings{DBLP:conf/naacl/MohiuddinJ19,
author = {Tasnim Mohiuddin and
Shafiq Rayhan Joty},
title = {Revisiting Adversarial Autoencoder for Unsupervised Word Translation
with Cycle Consistency and Improved Training},
pages = {3857--3867},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/HuangQC19,
author = {Jiaji Huang and
Qiang Qiu and
Kenneth Church},
title = {Hubless Nearest Neighbor Search for Bilingual Lexicon Induction},
pages = {4072--4080},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-1811-01124,
author = {Jean Alaux and
Edouard Grave and
Marco Cuturi and
Armand Joulin},
title = {Unsupervised Hyperalignment for Multilingual Word Embeddings},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/DouZH18,
author = {Zi-Yi Dou and
Zhi-Hao Zhou and
Shujian Huang},
title = {Unsupervised Bilingual Lexicon Induction via Latent Variable Models},
pages = {621--626},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/HoshenW18,
author = {Yedid Hoshen and
Lior Wolf},
title = {Non-Adversarial Unsupervised Word Translation},
pages = {469--478},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/KimGN18,
author = {Yunsu Kim and
Jiahui Geng and
Hermann Ney},
title = {Improving Unsupervised Word-by-Word Translation with Language Model
and Denoising Autoencoder},
pages = {862--868},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/MukherjeeYH18,
author = {Tanmoy Mukherjee and
Makoto Yamada and
Timothy Hospedales},
title = {Learning Unsupervised Word Translations Without Adversaries},
pages = {627--632},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/ChenC18,
author = {Xilun Chen and
Claire Cardie},
title = {Unsupervised Multilingual Word Embeddings},
pages = {261--270},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/TaitelbaumCG19,
author = {Hagai Taitelbaum and
Gal Chechik and
Jacob Goldberger},
title = {Multilingual word translation using auxiliary languages},
pages = {1330--1335},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:conf/acl/YangLCLS19,
author = {Pengcheng Yang and
Fuli Luo and
Peng Chen and
Tianyu Liu and
Xu Sun},
title = {{MAAM:} {A} Morphology-Aware Alignment Model for Unsupervised Bilingual
Lexicon Induction},
pages = {3190--3196},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/OrmazabalALSA19,
author = {Aitor Ormazabal and
Mikel Artetxe and
Gorka Labaka and
Aitor Soroa and
Eneko Agirre},
title = {Analyzing the Limitations of Cross-lingual Word Embedding Mappings},
pages = {4990--4995},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/ArtetxeLA19a,
author = {Mikel Artetxe and
Gorka Labaka and
Eneko Agirre},
title = {Bilingual Lexicon Induction through Unsupervised Machine Translation},
pages = {5002--5007},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/rep4nlp/VulicKG20,
author = {Ivan Vulic and
Anna Korhonen and
Goran Glavas},
title = {Improving Bilingual Lexicon Induction with Unsupervised Post-Processing
of Monolingual Word Vector Spaces},
pages = {45--54},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{hartmann2018empirical,
title={Empirical observations on the instability of aligning word vector spaces with GANs},
author={Hartmann, Mareike and Kementchedjhieva, Yova and S{\o}gaard, Anders},
publisher = {openreview.net},
year={2018}
}
@inproceedings{DBLP:conf/emnlp/Kementchedjhieva19,
author = {Yova Kementchedjhieva and
Mareike Hartmann and
Anders S{\o}gaard},
title = {Lost in Evaluation: Misleading Benchmarks for Bilingual Dictionary
Induction},
pages = {3334--3339},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:conf/nips/HartmannKS19,
author = {Mareike Hartmann and
Yova Kementchedjhieva and
Anders S{\o}gaard},
title = {Comparing Unsupervised Word Translation Methods Step by Step},
pages = {6031--6041},
publisher = {Annual Conference on Neural Information Processing Systems},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/HartmannKS18,
author = {Mareike Hartmann and
Yova Kementchedjhieva and
Anders S{\o}gaard},
title = {Why is unsupervised alignment of English embeddings from different
algorithms so hard?},
pages = {582--586},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/JoulinBMJG18,
author = {Armand Joulin and
Piotr Bojanowski and
Tomas Mikolov and
Herv{\'{e}} J{\'{e}}gou and
Edouard Grave},
title = {Loss in Translation: Learning Bilingual Word Mapping with a Retrieval
Criterion},
pages = {2979--2984},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/acl/SogaardVR18,
author = {Anders S{\o}gaard and
Sebastian Ruder and
Ivan Vulic},
title = {On the Limitations of Unsupervised Bilingual Dictionary Induction},
pages = {778--788},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/naacl/HeymanVVM19,
author = {Geert Heyman and
Bregt Verreet and
Ivan Vulic and
Marie-Francine Moens},
title = {Learning Unsupervised Multilingual Word Embeddings with Incremental
Multilingual Hubs},
pages = {1890--1902},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{2019ADabre,
title={A Survey of Multilingual Neural Machine Translation},
author={Dabre, Raj and Chu, Chenhui and Kunchukuttan, Anoop },
publisher={ACM Computing Surveys},
year={2019},
}
@inproceedings{DBLP:conf/naacl/ZophK16,
author = {Barret Zoph and
Kevin Knight},
title = {Multi-Source Neural Translation},
pages = {30--34},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/emnlp/KimPPKN19,
author = {Yunsu Kim and
Petre Petrov and
Pavel Petrushkov and
Shahram Khadivi and
Hermann Ney},
title = {Pivot-based Transfer Learning for Neural Machine Translation between
Non-English Languages},
pages = {866--876},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:journals/mt/WuW07,
author = {Hua Wu and
Haifeng Wang},
title = {Pivot language approach for phrase-based statistical machine translation},
publisher = {Machine Translation},
volume = {21},
number = {3},
pages = {165--181},
year = {2007}
}
@inproceedings{Farsi2010somayeh,
author = {Somayeh Bakhshaei and Shahram Khadivi and Noushin Riahi },
title = {Farsi-german statistical machine translation through bridge language},
publisher = {International Telecommunications Symposium},
pages = {165--181},
year = {2010}
}
@inproceedings{DBLP:conf/acl/ZahabiBK13,
author = {Samira Tofighi Zahabi and
Somayeh Bakhshaei and
Shahram Khadivi},
title = {Using Context Vectors in Improving a Machine Translation System with
Bridge Language},
pages = {318--322},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@inproceedings{DBLP:conf/emnlp/ZhuHWZWZ14,
author = {Xiaoning Zhu and
Zhongjun He and
Hua Wu and
Conghui Zhu and
Haifeng Wang and
Tiejun Zhao},
title = {Improving Pivot-Based Statistical Machine Translation by Pivoting
the Co-occurrence Count of Phrase Pairs},
pages = {1665--1675},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2014}
}
@inproceedings{DBLP:conf/acl/MiuraNSTN15,
author = {Akiva Miura and
Graham Neubig and
Sakriani Sakti and
Tomoki Toda and
Satoshi Nakamura},
title = {Improving Pivot Translation by Remembering the Pivot},
pages = {573--577},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:conf/acl/CohnL07,
author = {Trevor Cohn and
Mirella Lapata},
title = {Machine Translation by Triangulation: Making Effective Use of Multi-Parallel
Corpora},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/acl/WuW09,
author = {Hua Wu and
Haifeng Wang},
title = {Revisiting Pivot Language Approach for Machine Translation},
pages = {154--162},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{DBLP:journals/corr/ChengLYSX16,
author = {Yong Cheng and
Yang Liu and
Qian Yang and
Maosong Sun and
Wei Xu},
title = {Neural Machine Translation with Pivot Languages},
publisher = {CoRR},
volume = {abs/1611.04928},
year = {2016}
}
@inproceedings{DBLP:conf/interspeech/KauersVFW02,
author = {Manuel Kauers and
Stephan Vogel and
Christian F{\"{u}}gen and
Alex Waibel},
title = {Interlingua based statistical machine translation},
publisher = {International Symposium on Computer Architecture},
year = {2002}
}
@inproceedings{de2006catalan,
title={Catalan-English statistical machine translation without parallel corpus: bridging through Spanish},
author={De Gispert, Adri{\`a} and Marino, Jose B},
publisher={International Conference on Language Resources and Evaluation},
pages={65--68},
year={2006}
}
@inproceedings{DBLP:conf/naacl/UtiyamaI07,
author = {Masao Utiyama and
Hitoshi Isahara},
title = {A Comparison of Pivot Methods for Phrase-Based Statistical Machine
Translation},
pages = {484--491},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/ijcnlp/Costa-JussaHB11,
author = {Marta R. Costa-juss{\`{a}} and
Carlos A. Henr{\'{\i}}quez Q. and
Rafael E. Banchs},
title = {Enhancing scarce-resource language translation through pivot combinations},
pages = {1361--1365},
publisher = {International Joint Conference on Natural Language Processing},
year = {2011}
}
@inproceedings{DBLP:journals/corr/HintonVD15,
author = {Geoffrey E. Hinton and
Oriol Vinyals and
Jeffrey Dean},
title = {Distilling the Knowledge in a Neural Network},
publisher = {CoRR},
volume = {abs/1503.02531},
year = {2015}
}
@inproceedings{gu2018meta,
author = {Jiatao Gu and
Yong Wang and
Yun Chen and
Victor O. K. Li and
Kyunghyun Cho},
title = {Meta-Learning for Low-Resource Neural Machine Translation},
pages = {3622--3631},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/naacl/GuHDL18,
author = {Jiatao Gu and
Hany Hassan and
Jacob Devlin and
Victor O. K. Li},
title = {Universal Neural Machine Translation for Extremely Low Resource Languages},
pages = {344--354},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/icml/FinnAL17,
author = {Chelsea Finn and
Pieter Abbeel and
Sergey Levine},
title = {Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks},
series = {Proceedings of Machine Learning Research},
volume = {70},
pages = {1126--1135},
publisher = {International Conference on Machine Learning},
year = {2017}
}
@inproceedings{DBLP:conf/acl/DongWHYW15,
author = {Daxiang Dong and
Hua Wu and
Wei He and
Dianhai Yu and
Haifeng Wang},
title = {Multi-Task Learning for Multiple Language Translation},
pages = {1723--1732},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:conf/lrec/RiktersPK18,
author = {Matiss Rikters and
Marcis Pinnis and
Rihards Krislauks},
title = {Training and Adapting Multilingual {NMT} for Less-resourced and Morphologically
Rich Languages},
publisher = {European Language Resources Association},
year = {2018}
}
@inproceedings{DBLP:journals/tkde/PanY10,
author = {Sinno Jialin Pan and
Qiang Yang},
title = {A Survey on Transfer Learning},
publisher = {IEEE Transactions on knowledge and data engineering},
volume = {22},
number = {10},
pages = {1345--1359},
year = {2010}
}
@book{2009Handbook,
title={Handbook Of Research On Machine Learning Applications and Trends: Algorithms, Methods and Techniques - 2 Volumes},
author={Olivas, Emilio Soria and Guerrero, Jose David Martin and Sober, Marcelino Martinez and Benedito, Jose Rafael Magdalena and Lopez, Antonio Jose Serrano },
publisher={Information Science Reference - Imprint of: IGI Publishing},
year={2009},
}
@incollection{DBLP:books/crc/aggarwal14/Pan14,
author = {Sinno Jialin Pan},
title = {Transfer Learning},
publisher = {Data Classification: Algorithms and Applications},
pages = {537--570},
publisher = {{CRC} Press},
year = {2014}
}
@inproceedings{DBLP:conf/iclr/TanRHQZL19,
author = {Xu Tan and
Yi Ren and
Di He and
Tao Qin and
Zhou Zhao and
Tie-Yan Liu},
title = {Multilingual Neural Machine Translation with Knowledge Distillation},
publisher = {International Conference on Learning Representations},
year = {2019}
}
@inproceedings{platanios2018contextual,
author = {Emmanouil Antonios Platanios and
Mrinmaya Sachan and
Graham Neubig and
Tom M. Mitchell},
title = {Contextual Parameter Generation for Universal Neural Machine Translation},
pages = {425--435},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{ji2020cross,
title={Cross-Lingual Pre-Training Based Transfer for Zero-Shot Neural Machine Translation},
author={Ji, Baijun and Zhang, Zhirui and Duan, Xiangyu and Zhang, Min and Chen, Boxing and Luo, Weihua},
publisher={Proceedings of the AAAI Conference on Artificial Intelligence},
volume={34},
number={01},
pages={115--122},
year={2020}
}
@inproceedings{DBLP:conf/wmt/KocmiB18,
author = {Tom Kocmi and
Ondrej Bojar},
title = {Trivial Transfer Learning for Low-Resource Neural Machine Translation},
pages = {244--252},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/acl/ZhangWTS20,
author = {Biao Zhang and
Philip Williams and
Ivan Titov and
Rico Sennrich},
title = {Improving Massively Multilingual Neural Machine Translation and Zero-Shot
Translation},
pages = {1628--1639},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/naacl/PaulYSN09,
author = {Michael Paul and
Hirofumi Yamamoto and
Eiichiro Sumita and
Satoshi Nakamura},
title = {On the Importance of Pivot Language Selection for Statistical Machine
Translation},
pages = {221--224},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{dabre2020survey,
title={A survey of multilingual neural machine translation},
author={Dabre, Raj and Chu, Chenhui and Kunchukuttan, Anoop},
publisher={ACM Computing Surveys},
volume={53},
number={5},
pages={1--38},
year={2020}
}
@inproceedings{DBLP:conf/emnlp/XuYOW18,
author = {Ruochen Xu and
Yiming Yang and
Naoki Otani and
Yuexin Wu},
title = {Unsupervised Cross-lingual Transfer of Word Embedding Spaces},
pages = {2465--2474},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/ZhangLLS17,
author = {Meng Zhang and
Yang Liu and
Huanbo Luan and
Maosong Sun},
title = {Earth Mover's Distance Minimization for Unsupervised Bilingual Lexicon
Induction},
pages = {1934--1945},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/ArtetxeLA18,
author = {Mikel Artetxe and
Gorka Labaka and
Eneko Agirre},
title = {Unsupervised Statistical Machine Translation},
pages = {3632--3642},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:journals/tacl/LeeCH17,
author = {Jason Lee and
Kyunghyun Cho and
Thomas Hofmann},
title = {Fully Character-Level Neural Machine Translation without Explicit
Segmentation},
publisher = {Transactions of the Association for Computational Linguistics},
volume = {5},
pages = {365--378},
year = {2017}
}
@inproceedings{DBLP:conf/naacl/FiratCB16,
author = {Orhan Firat and
Kyunghyun Cho and
Yoshua Bengio},
title = {Multi-Way, Multilingual Neural Machine Translation with a Shared Attention
Mechanism},
pages = {866--875},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:journals/corr/HaNW16,
author = {Thanh-Le Ha and
Jan Niehues and
Alexander H. Waibel},
title = {Toward Multilingual Neural Machine Translation with Universal Encoder
and Decoder},
publisher = {CoRR},
volume = {abs/1611.04798},
year = {2016}
}
@inproceedings{DBLP:conf/coling/BlackwoodBW18,
author = {Graeme W. Blackwood and
Miguel Ballesteros and
Todd Ward},
title = {Multilingual Neural Machine Translation with Task-Specific Attention},
pages = {3112--3122},
publisher = {International Conference on Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/wmt/SachanN18,
author = {Devendra Singh Sachan and
Graham Neubig},
title = {Parameter Sharing Methods for Multilingual Self-Attentional Translation
Models},
pages = {261--271},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/wmt/LuKLBZS18,
author = {Yichao Lu and
Phillip Keung and
Faisal Ladhak and
Vikas Bhardwaj and
Shaonan Zhang and
Jason Sun},
title = {A neural interlingua for multilingual machine translation},
pages = {84--92},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/acl/WangZZZXZ19,
author = {Yining Wang and
Long Zhou and
Jiajun Zhang and
Feifei Zhai and
Jingfang Xu and
Chengqing Zong},
title = {A Compact and Language-Sensitive Multilingual Translation Method},
pages = {1213--1223},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/iclr/WangPAN19,
author = {Xinyi Wang and
Hieu Pham and
Philip Arthur and
Graham Neubig},
title = {Multilingual Neural Machine Translation With Soft Decoupled Encoding},
publisher = {International Conference on Learning Representations},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/TanCHXQL19,
author = {Xu Tan and
Jiale Chen and
Di He and
Yingce Xia and
Tao Qin and
Tie-Yan Liu},
title = {Multilingual Neural Machine Translation with Language Clustering},
pages = {963--973},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-1903-07091,
author = {Naveen Arivazhagan and
Ankur Bapna and
Orhan Firat and
Roee Aharoni and
Melvin Johnson and
Wolfgang Macherey},
title = {The Missing Ingredient in Zero-Shot Neural Machine Translation},
publisher = {CoRR},
volume = {abs/1903.07091},
year = {2019}
}
@inproceedings{DBLP:conf/naacl/Al-ShedivatP19,
author = {Maruan Al-Shedivat and
Ankur P. Parikh},
title = {Consistency by Agreement in Zero-Shot Neural Machine Translation},
pages = {1184--1197},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{firat2016zero,
author = {Orhan Firat and
Baskaran Sankaran and
Yaser Al-Onaizan and
Fatos T. Yarman-Vural and
Kyunghyun Cho},
title = {Zero-Resource Translation with Multi-Lingual Neural Machine Translation},
pages = {268--277},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2016}
}
@inproceedings{DBLP:journals/corr/abs-1805-10338,
author = {Lierni Sestorain and
Massimiliano Ciaramita and
Christian Buck and
Thomas Hofmann},
title = {Zero-Shot Dual Machine Translation},
publisher = {CoRR},
volume = {abs/1805.10338},
year = {2018}
}
@inproceedings{DBLP:conf/acl/GuWCL19,
author = {Jiatao Gu and
Yong Wang and
Kyunghyun Cho and
Victor O. K. Li},
title = {Improved Zero-shot Neural Machine Translation via Ignoring Spurious
Correlations},
pages = {1258--1268},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/FiratSAYC16,
author = {Orhan Firat and
Baskaran Sankaran and
Yaser Al-Onaizan and
Fatos T. Yarman-Vural and
Kyunghyun Cho},
title = {Zero-Resource Translation with Multi-Lingual Neural Machine Translation},
pages = {268--277},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2016}
}
@inproceedings{DBLP:conf/emnlp/CurreyH19,
author = {Anna Currey and
Kenneth Heafield},
title = {Zero-Resource Neural Machine Translation with Monolingual Pivot Data},
pages = {99--107},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:conf/acl/FadaeeBM17a,
author = {Marzieh Fadaee and
Arianna Bisazza and
Christof Monz},
title = {Data Augmentation for Low-Resource Neural Machine Translation},
pages = {567--573},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/WangPDN18,
author = {Xinyi Wang and
Hieu Pham and
Zihang Dai and
Graham Neubig},
title = {SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine
Translation},
pages = {856--861},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/MartonCR09,
author = {Yuval Marton and
Chris Callison-Burch and
Philip Resnik},
title = {Improved Statistical Machine Translation Using Monolingually-Derived
Paraphrases},
pages = {381--390},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{DBLP:conf/aclnmt/ImamuraFS18,
author = {Kenji Imamura and
Atsushi Fujita and
Eiichiro Sumita},
title = {Enhancement of Encoder and Attention Using Target Monolingual Corpora
in Neural Machine Translation},
pages = {55--63},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/icml/VincentLBM08,
author = {Pascal Vincent and
Hugo Larochelle and
Yoshua Bengio and
Pierre-Antoine Manzagol},
title = {Extracting and composing robust features with denoising autoencoders},
year = {2008},
publisher = {International Conference on Machine Learning}
}
@inproceedings{DBLP:conf/iclr/LampleCDR18,
author = {Guillaume Lample and
Alexis Conneau and
Ludovic Denoyer and
Marc'Aurelio Ranzato},
title = {Unsupervised Machine Translation Using Monolingual Corpora Only},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{DBLP:journals/coling/BhagatH13,
author = {Rahul Bhagat and
Eduard Hovy},
title = {What Is a Paraphrase?},
publisher = {Computational Linguistics},
volume = {39},
number = {3},
pages = {463--472},
year = {2013}
}
@inproceedings{2010Generating,
title={Generating Phrasal and Sentential Paraphrases: A Survey of Data-Driven Methods},
author={ Madnani, Nitin and Dorr, Bonnie},
publisher={Computational Linguistics},
volume={36},
number={3},
pages={341-387},
year={2010},
}
@inproceedings{DBLP:conf/wmt/GuoH19,
author = {Yinuo Guo and
Junfeng Hu},
title = {Meteor++ 2.0: Adopt Syntactic Level Paraphrase Knowledge into Machine
Translation Evaluation},
pages = {501--506},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/ZhouSW19,
author = {Zhong Zhou and
Matthias Sperber and
Alexander Waibel},
title = {Paraphrases as Foreign Languages in Multilingual Neural Machine Translation},
pages = {113--122},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/eacl/LapataSM17,
author = {Jonathan Mallinson and
Rico Sennrich and
Mirella Lapata},
title = {Paraphrasing Revisited with Neural Machine Translation},
pages = {881--893},
publisher = {Annual Conference of the European Association for Machine Translation},
year = {2017}
}
@inproceedings{DBLP:conf/naacl/SmithQT10,
author = {Jason Smith and
Chris Quirk and
Kristina Toutanova},
title = {Extracting Parallel Sentences from Comparable Corpora using Document
Level Alignment},
pages = {403--411},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2010}
}
@inproceedings{DBLP:journals/jair/RuderVS19,
author = {Sebastian Ruder and
Ivan Vulic and
Anders S{\o}gaard},
title = {A Survey of Cross-lingual Word Embedding Models},
publisher = {Journal of Artificial Intelligence Research},
volume = {65},
pages = {569--631},
year = {2019}
}
@inproceedings{DBLP:conf/acl/TuLLLL16,
author = {Zhaopeng Tu and
Zhengdong Lu and
Yang Liu and
Xiaohua Liu and
Hang Li},
title = {Modeling Coverage for Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:journals/tacl/TuLLLL17,
author = {Zhaopeng Tu and
Yang Liu and
Zhengdong Lu and
Xiaohua Liu and
Hang Li},
title = {Context Gates for Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
volume = {5},
pages = {87--99},
year = {2017}
}
@inproceedings{DBLP:conf/wmt/WangCJYCLSWY17,
author = {Yuguang Wang and
Shanbo Cheng and
Liyang Jiang and
Jiajun Yang and
Wei Chen and
Muze Li and
Lin Shi and
Yanfeng Wang and
Hongtao Yang},
title = {Sogou Neural Machine Translation Systems for {WMT17}},
pages = {410--415},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{ng2019facebook,
author = {Nathan Ng and
Kyra Yee and
Alexei Baevski and
Myle Ott and
Michael Auli and
Sergey Edunov},
title = {Facebook FAIR's {WMT19} News Translation Task Submission},
pages = {314--319},
publisher = {Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/wmt/WangLLJZLLXZ18,
author = {Qiang Wang and
Bei Li and
Jiqiang Liu and
Bojian Jiang and
Zheyang Zhang and
Yinqiao Li and
Ye Lin and
Tong Xiao and
Jingbo Zhu},
title = {The NiuTrans Machine Translation System for {WMT18}},
pages = {528--534},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/wmt/LiLXLLLWZXWFCLL19,
author = {Bei Li and
Yinqiao Li and
Chen Xu and
Ye Lin and
Jiqiang Liu and
Hui Liu and
Ziyang Wang and
Yuhao Zhang and
Nuo Xu and
Zeyang Wang and
Kai Feng and
Hexuan Chen and
Tengbo Liu and
Yanyang Li and
Qiang Wang and
Tong Xiao and
Jingbo Zhu},
title = {The NiuTrans Machine Translation Systems for {WMT19}},
pages = {257--266},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/nips/DaiL15,
author = {Andrew Dai and
Quoc Le},
title = {Semi-supervised Sequence Learning},
pages = {3079--3087},
publisher = {Annual Conference on Neural Information Processing Systems},
year = {2015}
}
@inproceedings{DBLP:journals/corr/abs-1802-05365,
author = {Matthew Peters and
Mark Neumann and
Mohit Iyyer and
Matt Gardner and
Christopher Clark and
Kenton Lee and
Luke Zettlemoyer},
title = {Deep Contextualized Word Representations},
pages = {2227--2237},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/icml/CollobertW08,
author = {Ronan Collobert and
Jason Weston},
title = {A unified architecture for natural language processing: deep neural
networks with multitask learning},
volume = {307},
pages = {160--167},
publisher = {International Conference on Machine Learning},
year = {2008}
}
@inproceedings{DBLP:conf/aclwat/NeishiSTIYT17,
author = {Masato Neishi and
Jin Sakuma and
Satoshi Tohda and
Shonosuke Ishiwatari and
Naoki Yoshinaga and
Masashi Toyoda},
title = {A Bag of Useful Tricks for Practical Neural Machine Translation: Embedding
Layer Initialization and Large Batch Size},
pages = {99--109},
publisher = {Asian Federation of Natural Language Processing},
year = {2017}
}
@inproceedings{2018When,
title={When and Why are Pre-trainedWord Embeddings Useful for Neural Machine Translation?},
author={ Qi, Ye and Sachan, Devendra Singh and Felix, Matthieu and Padmanabhan, Sarguna Janani and Neubig, Graham },
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year={2018},
}
@inproceedings{DBLP:conf/acl/PetersABP17,
author = {Matthew Peters and
Waleed Ammar and
Chandra Bhagavatula and
Russell Power},
title = {Semi-supervised sequence tagging with bidirectional language models},
pages = {1756--1765},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/ImamuraS19,
author = {Kenji Imamura and
Eiichiro Sumita},
title = {Recycling a Pre-trained {BERT} Encoder for Neural Machine Translation},
pages = {23--31},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/naacl/EdunovBA19,
author = {Sergey Edunov and
Alexei Baevski and
Michael Auli},
title = {Pre-trained language model representations for language generation},
pages = {4052--4059},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-1908-06259,
author = {Tianyu He and
Xu Tan and
Tao Qin},
title = {Hard but Robust, Easy but Sensitive: How Encoder and Decoder Perform
in Neural Machine Translation},
publisher = {CoRR},
volume = {abs/1908.06259},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/QiYGLDCZ020,
author = {Weizhen Qi and
Yu Yan and
Yeyun Gong and
Dayiheng Liu and
Nan Duan and
Jiusheng Chen and
Ruofei Zhang and
Ming Zhou},
title = {ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training},
pages = {2401--2410},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@incollection{DBLP:books/sp/98/Caruana98,
author = {Rich Caruana},
title = {Multitask Learning},
pages = {95--133},
publisher = {Springer},
year = {1998}
}
@inproceedings{liu2019multi,
author = {Xiaodong Liu and
Pengcheng He and
Weizhu Chen and
Jianfeng Gao},
title = {Multi-Task Deep Neural Networks for Natural Language Understanding},
pages = {4487--4496},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:journals/corr/LuongLSVK15,
author = {Minh-Thang Luong and
Quoc V. Le and
Ilya Sutskever and
Oriol Vinyals and
Lukasz Kaiser},
title = {Multi-task Sequence to Sequence Learning},
publisher = {International Conference on Learning Representations},
year = {2016}
}
@inproceedings{DBLP:conf/emnlp/ZhangZ16,
author = {Jiajun Zhang and
Chengqing Zong},
title = {Exploiting Source-side Monolingual Data in Neural Machine Translation},
pages = {1535--1545},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2016}
}
@inproceedings{DBLP:journals/tacl/JohnsonSLKWCTVW17,
author = {Melvin Johnson and
Mike Schuster and
Quoc V. Le and
Maxim Krikun and
Yonghui Wu and
Zhifeng Chen and
Nikhil Thorat and
Fernanda B. Vi{\'{e}}gas and
Martin Wattenberg and
Greg Corrado and
Macduff Hughes and
Jeffrey Dean},
title = {Google's Multilingual Neural Machine Translation System: Enabling
Zero-Shot Translation},
publisher = {Transactions of the Association for Computational Linguistics},
volume = {5},
pages = {339--351},
year = {2017}
}
@inproceedings{DBLP:journals/csl/GulcehreFXCB17,
author = {{\c{C}}aglar G{\"{u}}l{\c{c}}ehre and
Orhan Firat and
Kelvin Xu and
Kyunghyun Cho and
Yoshua Bengio},
title = {On integrating a language model into neural machine translation},
publisher = {Computational Linguistics},
volume = {45},
pages = {137--148},
year = {2017}
}
@inproceedings{DBLP:conf/wmt/StahlbergCS18,
author = {Felix Stahlberg and
James Cross and
Veselin Stoyanov},
title = {Simple Fusion: Return of the Language Model},
pages = {204--211},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/iccv/SunSSG17,
author = {Chen Sun and
Abhinav Shrivastava and
Saurabh Singh and
Abhinav Gupta},
title = {Revisiting Unreasonable Effectiveness of Data in Deep Learning Era},
pages = {843--852},
publisher = {IEEE International Conference on Computer Vision},
year = {2017}
}
@inproceedings{DBLP:conf/acl/DuhNST13,
author = {Kevin Duh and
Graham Neubig and
Katsuhito Sudoh and
Hajime Tsukada},
title = {Adaptation Data Selection using Neural Language Models: Experiments
in Machine Translation},
pages = {678--683},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@inproceedings{DBLP:conf/wmt/FosterK07,
author = {George F. Foster and
Roland Kuhn},
title = {Mixture-Model Adaptation for {SMT}},
pages = {128--135},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/iwslt/BisazzaRF11,
author = {Arianna Bisazza and
Nick Ruiz and
Marcello Federico},
title = {Fill-up versus interpolation methods for phrase-based {SMT} adaptation},
pages = {136--143},
publisher = {International Workshop on Spoken Language Translation},
year = {2011}
}
@inproceedings{niehues2012detailed,
title={Detailed analysis of different strategies for phrase table adaptation in SMT},
author={Niehues, Jan and Waibel, Alex},
publisher={Association for Machine Translation in the Americas},
year={2012}
}
@inproceedings{DBLP:conf/acl/SennrichSA13,
author = {Rico Sennrich and
Holger Schwenk and
Walid Aransa},
title = {A Multi-Domain Translation Model Framework for Statistical Machine
Translation},
pages = {832--840},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@inproceedings{imamura2016multi,
title={Multi-domain adaptation for statistical machine translation based on feature augmentation},
author={Imamura, Kenji and Sumita, Eiichiro},
publisher={Association for Machine Translation in the Americas},
pages={79},
year={2016}
}
@inproceedings{DBLP:conf/emnlp/MatsoukasRZ09,
author = {Spyros Matsoukas and
Antti-Veikko I. Rosti and
Bing Zhang},
title = {Discriminative Corpus Weight Estimation for Machine Translation},
pages = {708--717},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2009}
}
@inproceedings{DBLP:conf/emnlp/FosterGK10,
author = {George F. Foster and
Cyril Goutte and
Roland Kuhn},
title = {Discriminative Instance Weighting for Domain Adaptation in Statistical
Machine Translation},
pages = {451--459},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2010}
}
@inproceedings{shah2012general,
title={A general framework to weight heterogeneous parallel data for model adaptation in statistical machine translation},
author={Shah, Kashif and Barrault, Lo{\i}c and Schwenk, Holger and Le Mans, France},
publisher={Machine Translation Summit},
year={2012}
}
@inproceedings{DBLP:conf/iwslt/MansourN12,
author = {Saab Mansour and
Hermann Ney},
title = {A simple and effective weighted phrase extraction for machine translation
adaptation},
pages = {193--200},
publisher = {International Symposium on Computer Architecture},
year = {2012}
}
@inproceedings{DBLP:conf/cncl/ZhouCZ15,
author = {Xinpeng Zhou and
Hailong Cao and
Tiejun Zhao},
title = {Domain Adaptation for {SMT} Using Sentence Weight},
volume = {9427},
pages = {153--163},
publisher = {Springer},
year = {2015}
}
@inproceedings{DBLP:conf/lrec/EckVW04,
author = {Matthias Eck and
Stephan Vogel and
Alex Waibel},
title = {Language Model Adaptation for Statistical Machine Translation Based
on Information Retrieval},
publisher = {International Conference on Language Resources and Evaluation},
year = {2004}
}
@inproceedings{DBLP:conf/coling/ZhaoEV04,
author = {Bing Zhao and
Matthias Eck and
Stephan Vogel},
title = {Language Model Adaptation for Statistical Machine Translation via
Structured Query Models},
publisher = {International Conference on Computational Linguistics},
year = {2004}
}
@inproceedings{DBLP:conf/acl/MooreL10,
author = {Robert C. Moore and
William D. Lewis},
title = {Intelligent Selection of Language Model Training Data},
pages = {220--224},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2010}
}
@inproceedings{DBLP:conf/coling/HoangS14,
author = {Cuong Hoang and
Khalil Sima'an},
title = {Latent Domain Translation Models in Mix-of-Domains Haystack},
pages = {1928--1939},
publisher = {International Conference on Computational Linguistics},
year = {2014}
}
@inproceedings{joty2015using,
title={Using joint models for domain adaptation in statistical machine translation},
author={Joty, Nadir Durrani Hassan Sajjad Shafiq and Vogel, Ahmed Abdelali Stephan},
publisher={Proceedings of MT Summit XV},
pages={117},
year={2015}
}
@inproceedings{chen2016bilingual,
title={Bilingual methods for adaptive training data selection for machine translation},
author={Chen, Boxing and Kuhn, Roland and Foster, George and Cherry, Colin and Huang, Fei},
publisher={Association for Machine Translation in the Americas},
pages={93--103},
year={2016}
}
@inproceedings{DBLP:conf/iwslt/Ueffing06,
author = {Nicola Ueffing},
title = {Using monolingual source-language data to improve {MT} performance},
pages = {174--181},
publisher = {International Symposium on Computer Architecture},
year = {2006}
}
@inproceedings{DBLP:conf/coling/WuWZ08,
author = {Hua Wu and
Haifeng Wang and
Chengqing Zong},
title = {Domain Adaptation for Statistical Machine Translation with Domain
Dictionary and Monolingual Corpora},
publisher = {International Conference on Computational Linguistics},
pages = {993--1000},
year = {2008}
}
@inproceedings{DBLP:conf/iwslt/Schwenk08,
author = {Holger Schwenk},
title = {Investigations on large-scale lightly-supervised training for statistical
machine translation},
pages = {182--189},
publisher = {International Symposium on Computer Architecture},
year = {2008}
}
@inproceedings{DBLP:conf/wmt/BertoldiF09,
author = {Nicola Bertoldi and
Marcello Federico},
title = {Domain Adaptation for Statistical Machine Translation with Monolingual
Resources},
pages = {182--189},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{DBLP:conf/wmt/LambertSSA11,
author = {Patrik Lambert and
Holger Schwenk and
Christophe Servan and
Sadaf Abdul-Rauf},
title = {Investigations on Translation Model Adaptation Using Monolingual Data},
pages = {284--293},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2011}
}
@inproceedings{DBLP:conf/eacl/Sennrich12,
author = {Rico Sennrich},
title = {Perplexity Minimization for Translation Model Domain Adaptation in
Statistical Machine Translation},
pages = {539--549},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2012}
}
@inproceedings{DBLP:conf/wmt/ShahBS10,
author = {Kashif Shah and
Lo{\"{\i}}c Barrault and
Holger Schwenk},
title = {Translation Model Adaptation by Resampling},
pages = {392--399},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2010}
}
@inproceedings{rousseau2011lium,
title={LIUM's systems for the IWSLT 2011 Speech Translation Tasks},
author={Rousseau, Anthony and Bougares, Fethi and Del{\'e}glise, Paul and Schwenk, Holger and Est{\`e}ve, Yannick},
publisher={International Workshop on Spoken Language Translation},
year={2011}
}
@inproceedings{moore2010intelligent,
title = {Intelligent selection of language model training data},
author = {Moore, Robert C and Lewis, Will},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2010}
}
@inproceedings{DBLP:conf/acl/UtiyamaI03,
author = {Masao Utiyama and
Hitoshi Isahara},
title = {Reliable Measures for Aligning Japanese-English News Articles and
Sentences},
pages = {72--79},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2003}
}
@inproceedings{DBLP:conf/acl/MarieF17,
author = {Benjamin Marie and
Atsushi Fujita},
title = {Efficient Extraction of Pseudo-Parallel Sentences from Raw Monolingual
Data Using Word Embeddings},
pages = {392--398},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/WangZLUS14,
author = {Rui Wang and
Hai Zhao and
Bao-Liang Lu and
Masao Utiyama and
Eiichiro Sumita},
title = {Neural Network Based Bilingual Language Model Growing for Statistical
Machine Translation},
pages = {189--195},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/coling/WangZLUS16,
author = {Rui Wang and
Hai Zhao and
Bao-Liang Lu and
Masao Utiyama and
Eiichiro Sumita},
title = {Connecting Phrase based Statistical Machine Translation Adaptation},
pages = {3135--3145},
publisher = {International Conference on Computational Linguistics},
year = {2016}
}
@inproceedings{chu2015integrated,
title={Integrated parallel data extraction from comparable corpora for statistical machine translation},
author={Chu, Chenhui},
year={2015},
publisher={Kyoto University}
}
@inproceedings{DBLP:journals/tit/Scudder65a,
author = {H. J. Scudder III},
title = {Probability of error of some adaptive pattern-recognition machines},
publisher = {{IEEE} Transactions on Information Theory},
volume = {11},
number = {3},
pages = {363--371},
year = {1965}
}
@inproceedings{DBLP:conf/coling/ChuW18,
author = {Chenhui Chu and
Rui Wang},
title = {A Survey of Domain Adaptation for Neural Machine Translation},
pages = {1304--1319},
publisher = {International Conference on Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:journals/corr/abs-1708-08712,
author = {Hassan Sajjad and
Nadir Durrani and
Fahim Dalvi and
Yonatan Belinkov and
Stephan Vogel},
title = {Neural Machine Translation Training in a Multi-Domain Scenario},
publisher = {CoRR},
volume = {abs/1708.08712},
year = {2017}
}
@inproceedings{DBLP:conf/acl/WangTNYCP20,
author = {Wei Wang and
Ye Tian and
Jiquan Ngiam and
Yinfei Yang and
Isaac Caswell and
Zarana Parekh},
title = {Learning a Multi-Domain Curriculum for Neural Machine Translation},
pages = {7711--7723},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/acl/JiangLWZ20,
author = {Haoming Jiang and
Chen Liang and
Chong Wang and
Tuo Zhao},
title = {Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise
Domain Mixing},
pages = {1823--1834},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/emnlp/AxelrodHG11,
author = {Amittai Axelrod and
Xiaodong He and
Jianfeng Gao},
title = {Domain Adaptation via Pseudo In-Domain Data Selection},
pages = {355--362},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2011}
}
@inproceedings{DBLP:conf/icdm/Remus12,
author = {Robert Remus},
title = {Domain Adaptation Using Domain Similarity- and Domain Complexity-Based
Instance Selection for Cross-Domain Sentiment Analysis},
pages = {717--723},
publisher = {International Conference on Data Mining Workshops},
year = {2012}
}
@inproceedings{DBLP:conf/acl/WangFUS17,
author = {Rui Wang and
Andrew M. Finch and
Masao Utiyama and
Eiichiro Sumita},
title = {Sentence Embedding for Neural Machine Translation Domain Adaptation},
pages = {560--566},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/acl/HuXNC19,
author = {Junjie Hu and
Mengzhou Xia and
Graham Neubig and
Jaime G. Carbonell},
title = {Domain Adaptation of Neural Machine Translation by Lexicon Induction},
pages = {2989--3001},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{britz2017effective,
title={Effective domain mixing for neural machine translation},
author={Britz, Denny and Le, Quoc and Pryzant, Reid},
publisher={Proceedings of the Second Conference on Machine Translation},
pages={118--126},
year={2017}
}
@inproceedings{DBLP:conf/ranlp/KobusCS17,
author = {Catherine Kobus and
Josep Maria Crego and
Jean Senellart},
title = {Domain Control for Neural Machine Translation},
pages = {372--378},
publisher = {International Conference Recent Advances in Natural
Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/WangULCS17,
author = {Rui Wang and
Masao Utiyama and
Lemao Liu and
Kehai Chen and
Eiichiro Sumita},
title = {Instance Weighting for Neural Machine Translation Domain Adaptation},
pages = {1482--1488},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/aclnmt/ChenCFL17,
author = {Boxing Chen and
Colin Cherry and
George F. Foster and
Samuel Larkin},
title = {Cost Weighting for Neural Machine Translation Domain Adaptation},
pages = {40--46},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:journals/corr/abs-1906-03129,
author = {Shen Yan and
Leonard Dahlmann and
Pavel Petrushkov and
Sanjika Hewavitharana and
Shahram Khadivi},
title = {Word-based Domain Adaptation for Neural Machine Translation},
publisher = {CoRR},
volume = {abs/1906.03129},
year = {2019}
}
@inproceedings{dakwale2017finetuning,
title={Finetuning for neural machine translation with limited degradation across in-and out-of-domain data},
author={Dakwale, Praveen and Monz, Christof},
publisher={Proceedings of the XVI Machine Translation Summit},
volume={117},
year={2017}
}
@inproceedings{DBLP:conf/emnlp/ZengLSGLYL19,
author = {Jiali Zeng and
Yang Liu and
Jinsong Su and
Yubin Ge and
Yaojie Lu and
Yongjing Yin and
Jiebo Luo},
title = {Iterative Dual Domain Adaptation for Neural Machine Translation},
pages = {845--855},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{barone2017regularization,
author = {Antonio Valerio Miceli Barone and
Barry Haddow and
Ulrich Germann and
Rico Sennrich},
title = {Regularization techniques for fine-tuning in neural machine translation},
pages = {1489--1494},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/acl/SaundersB20,
author = {Danielle Saunders and
Bill Byrne},
title = {Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation
Problem},
pages = {7724--7736},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{khayrallah2017neural,
title={Neural lattice search for domain adaptation in machine translation},
author={Khayrallah, Huda and Kumar, Gaurav and Duh, Kevin and Post, Matt and Koehn, Philipp},
publisher={International Joint Conference on Natural Language Processing},
pages={20--25},
year={2017}
}
@inproceedings{DBLP:conf/emnlp/DouWHN19,
author = {Zi-Yi Dou and
Xinyi Wang and
Junjie Hu and
Graham Neubig},
title = {Domain Differential Adaptation for Neural Machine Translation},
pages = {59--69},
publisher = {Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:journals/corr/FreitagA16,
author = {Markus Freitag and
Yaser Al-Onaizan},
title = {Fast Domain Adaptation for Neural Machine Translation},
publisher = {CoRR},
volume = {abs/1612.06897},
year = {2016}
}
@inproceedings{DBLP:conf/acl/SaundersSGB19,
author = {Danielle Saunders and
Felix Stahlberg and
Adri{\`{a}} de Gispert and
Bill Byrne},
title = {Domain Adaptive Inference for Neural Machine Translation},
pages = {222--228},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/wmt/BritzLP17,
author = {Denny Britz and
Quoc V. Le and
Reid Pryzant},
title = {Effective Domain Mixing for Neural Machine Translation},
pages = {118--126},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:journals/ibmrd/Luhn58,
author = {Hans Peter Luhn},
title = {The Automatic Creation of Literature Abstracts},
publisher = {IBM Journal of research and development},
volume = {2},
number = {2},
pages = {159--165},
year = {1958}
}
@inproceedings{DBLP:conf/emnlp/DomhanH17,
author = {Tobias Domhan and
Felix Hieber},
title = {Using Target-side Monolingual Data for Neural Machine Translation
through Multi-task Learning},
pages = {1500--1505},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/naacl/SimianerWD19,
author = {Patrick Simianer and
Joern Wuebker and
John DeNero},
title = {Measuring Immediate Adaptation Performance for Neural Machine Translation},
pages = {2038--2046},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/WeesBM17,
author = {Marlies van der Wees and
Arianna Bisazza and
Christof Monz},
title = {Dynamic Data Selection for Neural Machine Translation},
pages = {1400--1410},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/naacl/ZhangSKMCD19,
author = {Xuan Zhang and
Pamela Shapiro and
Gaurav Kumar and
Paul McNamee and
Marine Carpuat and
Kevin Duh},
title = {Curriculum Learning for Domain Adaptation in Neural Machine Translation},
pages = {1903--1915},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/ChuDK17,
author = {Chenhui Chu and
Raj Dabre and
Sadao Kurohashi},
title = {An Empirical Comparison of Domain Adaptation Methods for Neural Machine
Translation},
pages = {385--391},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/naacl/BapnaF19,
author = {Ankur Bapna and
Orhan Firat},
title = {Non-Parametric Adaptation for Neural Machine Translation},
pages = {1921--1931},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-2010-11125,
author = {Angela Fan and
Shruti Bhosale and
Holger Schwenk and
Zhiyi Ma and
Ahmed El-Kishky and
Siddharth Goyal and
Mandeep Baines and
Onur Celebi and
Guillaume Wenzek and
Vishrav Chaudhary and
Naman Goyal and
Tom Birch and
Vitaliy Liptchinsky and
Sergey Edunov and
Edouard Grave and
Michael Auli and
Armand Joulin},
title = {Beyond English-Centric Multilingual Machine Translation},
publisher = {CoRR},
volume = {abs/2010.11125},
year = {2020}
}
@inproceedings{DBLP:conf/emnlp/LinPWQFZL20,
author = {Zehui Lin and
Xiao Pan and
Mingxuan Wang and
Xipeng Qiu and
Jiangtao Feng and
Hao Zhou and
Lei Li},
title = {Pre-training Multilingual Neural Machine Translation by Leveraging
Alignment Information},
pages = {2649--2663},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2020}
}
@inproceedings{DBLP:conf/emnlp/ZhuH07,
author = {Jingbo Zhu and
Eduard H. Hovy},
title = {Active Learning for Word Sense Disambiguation with Methods for Addressing
the Class Imbalance Problem},
pages = {783--790},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2007}
}
@inproceedings{DBLP:conf/eacl/NegriTFBF17,
author = {Mohammad Amin Farajian and
Marco Turchi and
Matteo Negri and
Nicola Bertoldi and
Marcello Federico},
title = {Neural vs. Phrase-Based Machine Translation in a Multi-Domain Scenario},
pages = {280--284},
publisher = {Annual Conference of the European Association for Machine Translation},
year = {2017}
}
@inproceedings{DBLP:conf/aaai/Zhang0LZC18,
author = {Zhirui Zhang and
Shujie Liu and
Mu Li and
Ming Zhou and
Enhong Chen},
title = {Joint Training for Neural Machine Translation Models with Monolingual
Data},
pages = {555--562},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2018}
}
@inproceedings{DBLP:conf/wmt/SunJXHWW19,
author = {Meng Sun and
Bojian Jiang and
Hao Xiong and
Zhongjun He and
Hua Wu and
Haifeng Wang},
title = {Baidu Neural Machine Translation Systems for {WMT19}},
pages = {374--381},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/SuHC19,
author = {Shang-Yu Su and
Chao-Wei Huang and
Yun-Nung Chen},
title = {Dual Supervised Learning for Natural Language Understanding and Generation},
pages = {5472--5477},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:journals/ejasmp/RadzikowskiNWY19,
author = {Kacper Radzikowski and
Robert Nowak and
Le Wang and
Osamu Yoshie},
title = {Dual supervised learning for non-native speech recognition},
publisher = {EURASIP Journal on Audio, Speech, and Music Processing},
volume = {2019},
pages = {3},
year = {2019}
}
@incollection{qin2020dual,
title={Dual Learning for Machine Translation and Beyond},
author={Qin, Tao},
pages={49--72},
year={2020},
publisher={Springer}
}
@inproceedings{DBLP:conf/iccv/YiZTG17,
author = {Zili Yi and
Hao (Richard) Zhang and
Ping Tan and
Minglun Gong},
title = {DualGAN: Unsupervised Dual Learning for Image-to-Image Translation},
pages = {2868--2876},
publisher = {{IEEE} Computer Society},
year = {2017}
}
@inproceedings{DBLP:journals/access/DuRZH20,
author = {Liang Du and
Xin Ren and
Peng Zhou and
Zhiguo Hu},
title = {Unsupervised Dual Learning for Feature and Instance Selection},
publisher = {{IEEE} Access},
volume = {8},
pages = {170248--170260},
year = {2020}
}
@inproceedings{DBLP:conf/acl/MarieRF20,
author = {Benjamin Marie and
Raphael Rubino and
Atsushi Fujita},
title = {Tagged Back-translation Revisited: Why Does It Really Work?},
pages = {5990--5997},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/nips/YangDYCSL19,
author = {Zhilin Yang and
Zihang Dai and
Yiming Yang and
Jaime G. Carbonell and
Ruslan Salakhutdinov and
Quoc V. Le},
title = {XLNet: Generalized Autoregressive Pretraining for Language Understanding},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {5754--5764},
year = {2019}
}
@inproceedings{DBLP:conf/iclr/LanCGGSS20,
author = {Zhenzhong Lan and
Mingda Chen and
Sebastian Goodman and
Kevin Gimpel and
Piyush Sharma and
Radu Soricut},
title = {{ALBERT:} {A} Lite {BERT} for Self-supervised Learning of Language
Representations},
publisher = {International Conference on Learning Representations},
year = {2020}
}
@inproceedings{DBLP:conf/acl/ZhangHLJSL19,
author = {Zhengyan Zhang and
Xu Han and
Zhiyuan Liu and
Xin Jiang and
Maosong Sun and
Qun Liu},
title = {{ERNIE:} Enhanced Language Representation with Informative Entities},
pages = {1441--1451},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/HuangLDGSJZ19,
author = {Haoyang Huang and
Yaobo Liang and
Nan Duan and
Ming Gong and
Linjun Shou and
Daxin Jiang and
Ming Zhou},
title = {Unicoder: {A} Universal Language Encoder by Pre-training with Multiple
Cross-lingual Tasks},
pages = {2485--2494},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:conf/iccv/SunMV0S19,
author = {Chen Sun and
Austin Myers and
Carl Vondrick and
Kevin Murphy and
Cordelia Schmid},
title = {VideoBERT: {A} Joint Model for Video and Language Representation Learning},
pages = {7463--7472},
publisher = {International Conference on Computer Vision},
year = {2019}
}
@inproceedings{DBLP:journals/corr/abs-2010-12831,
author = {Liunian Harold Li and
Haoxuan You and
Zhecan Wang and
Alireza Zareian and
Shih-Fu Chang and
Kai-Wei Chang},
title = {Weakly-supervised VisualBERT: Pre-training without Parallel Images
and Captions},
publisher = {CoRR},
volume = {abs/2010.12831},
year = {2020}
}
@inproceedings{DBLP:conf/nips/LuBPL19,
author = {Jiasen Lu and
Dhruv Batra and
Devi Parikh and
Stefan Lee},
title = {ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations
for Vision-and-Language Tasks},
publisher = {Annual Annual Conference on Neural Information Processing Systems},
pages = {13--23},
year = {2019}
}
@inproceedings{DBLP:conf/interspeech/ChuangLLL20,
author = {Yung-Sung Chuang and
Chi-Liang Liu and
Hung-yi Lee and
Lin-Shan Lee},
title = {SpeechBERT: An Audio-and-Text Jointly Learned Language Model for End-to-End
Spoken Question Answering},
pages = {4168--4172},
publisher = {Annual Conference of the International Speech Communication Association},
year = {2020}
}
@inproceedings{DBLP:conf/rep4nlp/PetersRS19,
author = {Matthew Peters and
Sebastian Ruder and
Noah A. Smith},
title = {To Tune or Not to Tune? Adapting Pretrained Representations to Diverse
Tasks},
pages = {7--14},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/cncl/SunQXH19,
author = {Chi Sun and
Xipeng Qiu and
Yige Xu and
Xuanjing Huang},
title = {How to Fine-Tune {BERT} for Text Classification?},
volume = {11856},
pages = {194--206},
publisher = {Chinese Computational Linguistics},
year = {2019}
}
@inproceedings{shen2020q,
title={Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT.},
author={Shen, Sheng and Dong, Zhen and Ye, Jiayu and Ma, Linjian and Yao, Zhewei and Gholami, Amir and Mahoney, Michael W and Keutzer, Kurt},
publisher={AAAI Conference on Artificial Intelligence},
pages={8815--8821},
year={2020}
}
@inproceedings{DBLP:journals/corr/abs-1910-01108,
author = {Victor Sanh and
Lysandre Debut and
Julien Chaumond and
Thomas Wolf},
title = {DistilBERT, a distilled version of {BERT:} smaller, faster, cheaper
and lighter},
publisher = {CoRR},
volume = {abs/1910.01108},
year = {2019}
}
@inproceedings{DBLP:conf/icml/XiaTTQYL18,
author = {Yingce Xia and
Xu Tan and
Fei Tian and
Tao Qin and
Nenghai Yu and
Tie-Yan Liu},
title = {Model-Level Dual Learning},
series = {Proceedings of Machine Learning Research},
volume = {80},
pages = {5379--5388},
publisher = {International Conference on Machine Learning},
year = {2018}
}
@inproceedings{DBLP:conf/nips/HeXQWYLM16,
author = {Di He and
Yingce Xia and
Tao Qin and
Liwei Wang and
Nenghai Yu and
Tie-Yan Liu and
Wei-Ying Ma},
title = {Dual Learning for Machine Translation},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {820--828},
year = {2016}
}
@article{zhao2020dual,
title={Dual Learning: Theoretical Study and an Algorithmic Extension},
author={Zhao, Zhibing and Xia, Yingce and Qin, Tao and Xia, Lirong and Liu, Tie-Yan},
journal={arXiv preprint arXiv:2005.08238},
year={2020}
}
%%%%% chapter 16------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 17------------------------------------------------------
@article{DBLP:journals/ac/Bar-Hillel60,
author = {Yehoshua Bar-Hillel},
title = {The Present Status of Automatic Translation of Languages},
journal = {Advances in computers},
volume = {1},
pages = {91--163},
year = {1960}
}
@article{DBLP:journals/corr/abs-1901-09115,
author = {Andrei Popescu-Belis},
title = {Context in Neural Machine Translation: {A} Review of Models and Evaluations},
journal = {CoRR},
volume = {abs/1901.09115},
year = {2019}
}
@book{jurafsky2000speech,
title={Speech \& language processing},
author={Jurafsky, Dan},
year={2000},
publisher={Pearson Education India}
}
@inproceedings{DBLP:conf/anlp/MarcuCW00,
author = {Daniel Marcu and
Lynn Carlson and
Maki Watanabe},
title = {The Automatic Translation of Discourse Structures},
pages = {9--17},
publisher = {Applied Natural Language Processing Conference},
year = {2000}
}
@inproceedings{foster2010translating,
title={Translating structured documents},
author={Foster, George and Isabelle, Pierre and Kuhn, Roland},
booktitle={Proceedings of AMTA},
year={2010}
}
@inproceedings{DBLP:conf/eacl/LouisW14,
author = {Annie Louis and
Bonnie L. Webber},
title = {Structured and Unstructured Cache Models for {SMT} Domain Adaptation},
pages = {155--163},
publisher = {Annual Conference of the European Association for Machine Translation},
year = {2014}
}
@inproceedings{DBLP:conf/iwslt/HardmeierF10,
author = {Christian Hardmeier and
Marcello Federico},
title = {Modelling pronominal anaphora in statistical machine translation},
pages = {283--289},
publisher = {International Workshop on Spoken Language Translation},
year = {2010}
}
@inproceedings{DBLP:conf/wmt/NagardK10,
author = {Ronan Le Nagard and
Philipp Koehn},
title = {Aiding Pronoun Translation with Co-Reference Resolution},
pages = {252--261},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2010}
}
@inproceedings{DBLP:conf/eamt/LuongP16,
author = {Ngoc-Quang Luong and
Andrei Popescu-Belis},
title = {A Contextual Language Model to Improve Machine Translation of Pronouns
by Re-ranking Translation Hypotheses},
pages = {292--304},
publisher = {European Association for Machine Translation},
year = {2016}
}
@inproceedings{tiedemann2010context,
title={Context adaptation in statistical machine translation using models with exponentially decaying cache},
author={Tiedemann, J{\"o}rg},
publisher={Domain Adaptation for Natural Language Processing},
pages={8--15},
year={2010}
}
@inproceedings{DBLP:conf/emnlp/GongZZ11,
author = {Zhengxian Gong and
Min Zhang and
Guodong Zhou},
title = {Cache-based Document-level Statistical Machine Translation},
pages = {909--919},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2011}
}
@inproceedings{DBLP:conf/ijcai/XiongBZLL13,
author = {Deyi Xiong and
Guosheng Ben and
Min Zhang and
Yajuan Lv and
Qun Liu},
title = {Modeling Lexical Cohesion for Document-Level Machine Translation},
pages = {2183--2189},
publisher = { International Joint Conference on Artificial Intelligence},
year = {2013}
}
@inproceedings{xiao2011document,
title={Document-level consistency verification in machine translation},
author={Xiao, Tong and Zhu, Jingbo and Yao, Shujie and Zhang, Hao},
booktitle={Machine Translation Summit},
volume={13},
pages={131--138},
year={2011}
}
@inproceedings{DBLP:conf/sigdial/MeyerPZC11,
author = {Thomas Meyer and
Andrei Popescu-Belis and
Sandrine Zufferey and
Bruno Cartoni},
title = {Multilingual Annotation and Disambiguation of Discourse Connectives
for Machine Translation},
pages = {194--203},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2011}
}
@inproceedings{DBLP:conf/hytra/MeyerP12,
author = {Thomas Meyer and
Andrei Popescu-Belis},
title = {Using Sense-labeled Discourse Connectives for Statistical Machine
Translation},
pages = {129--138},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2012}
}
@inproceedings{DBLP:conf/nips/SutskeverVL14,
author = {Ilya Sutskever and
Oriol Vinyals and
Quoc V. Le},
title = {Sequence to Sequence Learning with Neural Networks},
pages = {3104--3112},
year = {2014},
publisher = {Annual Conference on Neural Information Processing Systems}
}
@inproceedings{DBLP:conf/emnlp/LaubliS018,
author = {Samuel L{\"{a}}ubli and
Rico Sennrich and
Martin Volk},
title = {Has Machine Translation Achieved Human Parity? {A} Case for Document-level
Evaluation},
pages = {4791--4796},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@article{DBLP:journals/corr/abs-1912-08494,
author = {Sameen Maruf and
Fahimeh Saleh and
Gholamreza Haffari},
title = {A Survey on Document-level Machine Translation: Methods and Evaluation},
journal = {CoRR},
volume = {abs/1912.08494},
year = {2019}
}
@inproceedings{DBLP:conf/discomt/TiedemannS17,
author = {J{\"{o}}rg Tiedemann and
Yves Scherrer},
title = {Neural Machine Translation with Extended Context},
pages = {82--92},
publisher = {Association for Computational Linguistics},
year = {2017}
}
@article{DBLP:journals/corr/abs-1910-07481,
author = {Valentin Mac{\'{e}} and
Christophe Servan},
title = {Using Whole Document Context in Neural Machine Translation},
journal = {CoRR},
volume = {abs/1910.07481},
year = {2019}
}
@article{DBLP:journals/corr/JeanLFC17,
author = {S{\'{e}}bastien Jean and
Stanislas Lauly and
Orhan Firat and
Kyunghyun Cho},
title = {Does Neural Machine Translation Benefit from Larger Context?},
journal = {CoRR},
volume = {abs/1704.05135},
year = {2017}
}
@inproceedings{DBLP:conf/acl/TitovSSV18,
author = {Elena Voita and
Pavel Serdyukov and
Rico Sennrich and
Ivan Titov},
title = {Context-Aware Neural Machine Translation Learns Anaphora Resolution},
pages = {1264--1274},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/acl/HaffariM18,
author = {Sameen Maruf and
Gholamreza Haffari},
title = {Document Context Neural Machine Translation with Memory Networks},
pages = {1275--1284},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/coling/KuangXLZ18,
author = {Shaohui Kuang and
Deyi Xiong and
Weihua Luo and
Guodong Zhou},
title = {Modeling Coherence for Neural Machine Translation with Dynamic and
Topic Caches},
pages = {596--606},
publisher = {International Conference on Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/discomt/GarciaCE19,
author = {Eva Mart{\'{\i}}nez Garcia and
Carles Creus and
Cristina Espa{\~{n}}a-Bonet},
title = {Context-Aware Neural Machine Translation Decoding},
pages = {13--23},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@article{DBLP:journals/corr/abs-2010-12827,
author = {Amane Sugiyama and
Naoki Yoshinaga},
title = {Context-aware Decoder for Neural Machine Translation using a Target-side
Document-Level Language Model},
journal = {CoRR},
volume = {abs/2010.12827},
year = {2020}
}
@inproceedings{DBLP:conf/acl/VoitaST19,
author = {Elena Voita and
Rico Sennrich and
Ivan Titov},
title = {When a Good Translation is Wrong in Context: Context-Aware Machine
Translation Improves on Deixis, Ellipsis, and Lexical Cohesion},
pages = {1198--1212},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/VoitaST19,
author = {Elena Voita and
Rico Sennrich and
Ivan Titov},
title = {Context-Aware Monolingual Repair for Neural Machine Translation},
pages = {877--886},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:conf/discomt/WerlenP17,
author = {Lesly Miculicich Werlen and
Andrei Popescu-Belis},
title = {Validation of an Automatic Metric for the Accuracy of Pronoun Translation
{(APT)}},
pages = {17--25},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/WongK12,
author = {Billy Tak-Ming Wong and
Chunyu Kit},
title = {Extending Machine Translation Evaluation Metrics with Lexical Cohesion
to Document Level},
pages = {1060--1068},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2012}
}
@inproceedings{DBLP:conf/discomt/GongZZ15,
author = {Zhengxian Gong and
Min Zhang and
Guodong Zhou},
title = {Document-Level Machine Translation Evaluation with Gist Consistency
and Text Cohesion},
pages = {33--40},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2015}
}
@inproceedings{DBLP:conf/cicling/HajlaouiP13,
author = {Najeh Hajlaoui and
Andrei Popescu-Belis},
title = {Assessing the Accuracy of Discourse Connective Translations: Validation
of an Automatic Metric},
volume = {7817},
pages = {236--247},
publisher = {Springer},
year = {2013}
}
@inproceedings{DBLP:conf/wmt/RiosMS18,
author = {Annette Rios and
Mathias M{\"{u}}ller and
Rico Sennrich},
title = {The Word Sense Disambiguation Test Suite at {WMT18}},
pages = {588--596},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/naacl/BawdenSBH18,
author = {Rachel Bawden and
Rico Sennrich and
Alexandra Birch and
Barry Haddow},
title = {Evaluating Discourse Phenomena in Neural Machine Translation},
pages = {1304--1313},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/wmt/MullerRVS18,
author = {Mathias M{\"{u}}ller and
Annette Rios and
Elena Voita and
Rico Sennrich},
title = {A Large-Scale Test Set for the Evaluation of Context-Aware Pronoun
Translation in Neural Machine Translation},
pages = {61--72},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/iclr/KitaevKL20,
author = {Nikita Kitaev and
Lukasz Kaiser and
Anselm Levskaya},
title = {Reformer: The Efficient Transformer},
publisher = {International Conference on Learning Representations},
year = {2020}
}
@inproceedings{agrawal2018contextual,
title={Contextual handling in neural machine translation: Look behind, ahead and on both sides},
author={Agrawal, Ruchit Rajeshkumar and Turchi, Marco and Negri, Matteo},
booktitle={Annual Conference of the European Association for Machine Translation},
pages={11--20},
year={2018}
}
@inproceedings{DBLP:conf/emnlp/WerlenRPH18,
author = {Lesly Miculicich Werlen and
Dhananjay Ram and
Nikolaos Pappas and
James Henderson},
title = {Document-Level Neural Machine Translation with Hierarchical Attention
Networks},
pages = {2947--2954},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/naacl/MarufMH19,
author = {Sameen Maruf and
Andr{\'{e}} F. T. Martins and
Gholamreza Haffari},
title = {Selective Attention for Context-aware Neural Machine Translation},
pages = {3092--3102},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/TanZXZ19,
author = {Xin Tan and
Longyin Zhang and
Deyi Xiong and
Guodong Zhou},
title = {Hierarchical Modeling of Global Context for Document-Level Neural
Machine Translation},
pages = {1576--1585},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/YangZMGFZ19,
author = {Zhengxin Yang and
Jinchao Zhang and
Fandong Meng and
Shuhao Gu and
Yang Feng and
Jie Zhou},
title = {Enhancing Context Modeling with a Query-Guided Capsule Network for
Document-level Translation},
pages = {1527--1537},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:conf/ijcai/ZhengYHCB20,
author = {Zaixiang Zheng and
Xiang Yue and
Shujian Huang and
Jiajun Chen and
Alexandra Birch},
title = {Towards Making the Most of Context in Neural Machine Translation},
pages = {3983--3989},
publisher = {International Joint Conference on Artificial Intelligence},
year = {2020}
}
@article{DBLP:journals/tacl/TuLSZ18,
author = {Zhaopeng Tu and
Yang Liu and
Shuming Shi and
Tong Zhang},
title = {Learning to Remember Translation History with a Continuous Cache},
publisher = {Transactions of the Association for Computational Linguistics},
volume = {6},
pages = {407--420},
year = {2018}
}
@inproceedings{DBLP:conf/discomt/ScherrerTL19,
author = {Yves Scherrer and
J{\"{o}}rg Tiedemann and
Sharid Lo{\'{a}}iciga},
title = {Analysing concatenation approaches to document-level {NMT} in two
different domains},
pages = {51--61},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/wmt/GonzalesMS17,
author = {Annette Rios Gonzales and
Laura Mascarell and
Rico Sennrich},
title = {Improving Word Sense Disambiguation in Neural Machine Translation
with Sense Embeddings},
pages = {11--19},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/acl/LiLWJXZLL20,
author = {Bei Li and
Hui Liu and
Ziyang Wang and
Yufan Jiang and
Tong Xiao and
Jingbo Zhu and
Tongran Liu and
Changliang Li},
title = {Does Multi-Encoder Help? {A} Case Study on Context-Aware Neural Machine
Translation},
pages = {3512--3518},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/discomt/KimTN19,
author = {Yunsu Kim and
Duc Thanh Tran and
Hermann Ney},
title = {When and Why is Document-level Context Useful in Neural Machine Translation?},
pages = {24--34},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/discomt/SugiyamaY19,
author = {Amane Sugiyama and
Naoki Yoshinaga},
title = {Data augmentation using back-translation for context-aware neural
machine translation},
pages = {35--44},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/pacling/YamagishiK19,
author = {Hayahide Yamagishi and
Mamoru Komachi},
title = {Improving Context-Aware Neural Machine Translation with Target-Side
Context},
volume = {1215},
pages = {112--122},
publisher = {Springer},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/ZhangLSZXZL18,
author = {Jiacheng Zhang and
Huanbo Luan and
Maosong Sun and
Feifei Zhai and
Jingfang Xu and
Min Zhang and
Yang Liu},
title = {Improving the Transformer Translation Model with Document-Level Context},
pages = {533--542},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/coling/KuangX18,
author = {Shaohui Kuang and
Deyi Xiong},
title = {Fusing Recency into Neural Machine Translation with an Inter-Sentence
Gate Model},
pages = {607--617},
publisher = {International Conference on Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/emnlp/WangTWL17,
author = {Longyue Wang and
Zhaopeng Tu and
Andy Way and
Qun Liu},
title = {Exploiting Cross-Sentence Context for Neural Machine Translation},
pages = {2826--2831},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/aaai/XiongH0W19,
author = {Hao Xiong and
Zhongjun He and
Hua Wu and
Haifeng Wang},
title = {Modeling Coherence for Discourse Neural Machine Translation},
pages = {7338--7345},
publisher = {{AAAI} Press},
year = {2019}
}
@article{DBLP:journals/tacl/YuSSLKBD20,
author = {Lei Yu and
Laurent Sartran and
Wojciech Stokowiec and
Wang Ling and
Lingpeng Kong and
Phil Blunsom and
Chris Dyer},
title = {Better Document-Level Machine Translation with Bayes' Rule},
journal = {Transactions of the Association for Computational Linguistics},
volume = {8},
pages = {346--360},
year = {2020}
}
@article{DBLP:journals/corr/abs-1903-04715,
author = {S{\'{e}}bastien Jean and
Kyunghyun Cho},
title = {Context-Aware Learning for Neural Machine Translation},
journal = {CoRR},
volume = {abs/1903.04715},
year = {2019}
}
@inproceedings{DBLP:conf/acl/SaundersSB20,
author = {Danielle Saunders and
Felix Stahlberg and
Bill Byrne},
title = {Using Context in Neural Machine Translation Training Objectives},
pages = {7764--7770},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/mtsummit/StojanovskiF19,
author = {Dario Stojanovski and
Alexander M. Fraser},
title = {Improving Anaphora Resolution in Neural Machine Translation Using
Curriculum Learning},
pages = {140--150},
publisher = {Annual Conference of the European Association for Machine Translation},
year = {2019}
}
@article{DBLP:journals/corr/abs-1911-03110,
author = {Liangyou Li and
Xin Jiang and
Qun Liu},
title = {Pretrained Language Models for Document-Level Neural Machine Translation},
publisher = {CoRR},
volume = {abs/1911.03110},
year = {2019}
}
@article{DBLP:journals/tacl/LiuGGLEGLZ20,
author = {Yinhan Liu and
Jiatao Gu and
Naman Goyal and
Xian Li and
Sergey Edunov and
Marjan Ghazvininejad and
Mike Lewis and
Luke Zettlemoyer},
title = {Multilingual Denoising Pre-training for Neural Machine Translation},
journal = {Transactions of the Association for Computational Linguistics},
volume = {8},
pages = {726--742},
year = {2020}
}
@inproceedings{DBLP:conf/wmt/MarufMH18,
author = {Sameen Maruf and
Andr{\'{e}} F. T. Martins and
Gholamreza Haffari},
title = {Contextual Neural Model for Translating Bilingual Multi-Speaker Conversations},
pages = {101--112},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/interspeech/SainathWSWV15,
author = {Tara N. Sainath and
Ron J. Weiss and
Andrew W. Senior and
Kevin W. Wilson and
Oriol Vinyals},
title = {Learning the speech front-end with raw waveform CLDNNs},
pages = {1--5},
publisher = {International Symposium on Computer Architecture},
year = {2015}
}
@inproceedings{DBLP:conf/icassp/MohamedHP12,
author = {Abdel-rahman Mohamed and
Geoffrey E. Hinton and
Gerald Penn},
title = {Understanding how Deep Belief Networks perform acoustic modelling},
pages = {4273--4276},
publisher = {IEEE Transactions on Acoustics, Speech, and Signal Processing},
year = {2012}
}
@article{DBLP:journals/ftsig/GalesY07,
author = {Mark J. F. Gales and
Steve J. Young},
title = {The Application of Hidden Markov Models in Speech Recognition},
journal = {Found Trends Signal Process},
volume = {1},
number = {3},
pages = {195--304},
year = {2007}
}
@article{DBLP:journals/taslp/MohamedDH12,
author = {Abdel-rahman Mohamed and
George E. Dahl and
Geoffrey E. Hinton},
title = {Acoustic Modeling Using Deep Belief Networks},
journal = {IEEE Transactions on Speech and Audio Processing},
volume = {20},
number = {1},
pages = {14--22},
year = {2012}
}
@article{DBLP:journals/spm/X12a,
title = {Deep Neural Networks for Acoustic Modeling in Speech Recognition:
The Shared Views of Four Research Groups},
journal = {IEEE Signal Processing Magazine},
volume = {29},
number = {6},
pages = {82--97},
year = {2012}
}
@inproceedings{DBLP:conf/nips/ChorowskiBSCB15,
author = {Jan Chorowski and
Dzmitry Bahdanau and
Dmitriy Serdyuk and
Kyunghyun Cho and
Yoshua Bengio},
title = {Attention-Based Models for Speech Recognition},
publisher = {Annual Conference on Neural Information Processing Systems},
pages = {577--585},
year = {2015}
}
@inproceedings{DBLP:conf/icassp/ChanJLV16,
author = {William Chan and
Navdeep Jaitly and
Quoc V. Le and
Oriol Vinyals},
title = {Listen, attend and spell: A neural network for large vocabulary
conversational speech recognition},
publisher = {IEEE Transactions on Acoustics, Speech, and Signal Processing},
pages = {4960--4964},
year = {2016}
}
@inproceedings{DBLP:conf/acl/ZhangGCF19,
author = {Pei Zhang and
Niyu Ge and
Boxing Chen and
Kai Fan},
title = {Lattice Transformer for Speech Translation},
pages = {6475--6484},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/SperberNPW19,
author = {Matthias Sperber and
Graham Neubig and
Ngoc-Quan Pham and
Alex Waibel},
title = {Self-Attentional Models for Lattice Inputs},
pages = {1185--1197},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/LiuTMCZ18,
author = {Yong Cheng and
Zhaopeng Tu and
Fandong Meng and
Junjie Zhai and
Yang Liu},
title = {Towards Robust Neural Machine Translation},
pages = {1756--1766},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/naacl/DuongACBC16,
author = {Long Duong and
Antonios Anastasopoulos and
David Chiang and
Steven Bird and
Trevor Cohn},
title = {An Attentional Model for Speech Translation Without Transcription},
pages = {949--959},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2016}
}
@article{DBLP:journals/corr/BerardPSB16,
author = {Alexandre Berard and
Olivier Pietquin and
Christophe Servan and
Laurent Besacier},
title = {Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text
Translation},
journal = {CoRR},
volume = {abs/1612.01744},
year = {2016}
}
@inproceedings{DBLP:conf/interspeech/WeissCJWC17,
author = {Ron J. Weiss and
Jan Chorowski and
Navdeep Jaitly and
Yonghui Wu and
Zhifeng Chen},
title = {Sequence-to-Sequence Models Can Directly Translate Foreign Speech},
pages = {2625--2629},
publisher = {International Symposium on Computer Architecture},
year = {2017}
}
@inproceedings{DBLP:conf/mtsummit/GangiNCDT19,
author = {Mattia Antonino Di Gangi and
Matteo Negri and
Roldano Cattoni and
Roberto Dess{\`{\i}} and
Marco Turchi},
title = {Enhancing Transformer for End-to-end Speech-to-Text Translation},
pages = {21--31},
publisher = {European Association for Machine Translation},
year = {2019}
}
@inproceedings{DBLP:conf/icml/GravesFGS06,
author = {Alex Graves and
Santiago Fern{\'{a}}ndez and
Faustino J. Gomez and
J{\"{u}}rgen Schmidhuber},
title = {Connectionist temporal classification: labelling unsegmented sequence
data with recurrent neural networks},
volume = {148},
pages = {369--376},
publisher = {International Conference on Machine Learning},
year = {2006}
}
@article{DBLP:journals/jstsp/WatanabeHKHH17,
author = {Shinji Watanabe and
Takaaki Hori and
Suyoun Kim and
John R. Hershey and
Tomoki Hayashi},
title = {Hybrid CTC/Attention Architecture for End-to-End Speech Recognition},
journal = {IEEE Journal of Selected Topics in Signal Processing},
volume = {11},
number = {8},
pages = {1240--1253},
year = {2017}
}
@inproceedings{DBLP:conf/icassp/KimHW17,
author = {Suyoun Kim and
Takaaki Hori and
Shinji Watanabe},
title = {Joint CTC-attention based end-to-end speech recognition using multi-task
learning},
pages = {4835--4839},
publisher = {IEEE Transactions on Acoustics, Speech, and Signal Processing},
year = {2017}
}
@article{DBLP:journals/pami/ShiBY17,
author = {Baoguang Shi and
Xiang Bai and
Cong Yao},
title = {An End-to-End Trainable Neural Network for Image-Based Sequence Recognition
and Its Application to Scene Text Recognition},
journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence},
volume = {39},
number = {11},
pages = {2298--2304},
year = {2017}
}
@inproceedings{DBLP:conf/naacl/AnastasopoulosC18,
author = {Antonios Anastasopoulos and
David Chiang},
title = {Tied Multitask Learning for Neural Speech Translation},
pages = {82--91},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/asru/BaharBN19,
author = {Parnia Bahar and
Tobias Bieschke and
Hermann Ney},
title = {A Comparative Study on End-to-End Speech to Text Translation},
pages = {792--799},
publisher = { IEEE Automatic Speech Recognition and Understanding Workshop},
year = {2019}
}
@inproceedings{DBLP:conf/naacl/BansalKLLG19,
author = {Sameer Bansal and
Herman Kamper and
Karen Livescu and
Adam Lopez and
Sharon Goldwater},
title = {Pre-training on high-resource speech recognition improves low-resource
speech-to-text translation},
pages = {58--68},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/icassp/BerardBKP18,
author = {Alexandre Berard and
Laurent Besacier and
Ali Can Kocabiyikoglu and
Olivier Pietquin},
title = {End-to-End Automatic Speech Translation of Audiobooks},
pages = {6224--6228},
publisher = {IEEE Transactions on Acoustics, Speech, and Signal Processing},
year = {2018}
}
@inproceedings{DBLP:conf/icassp/JiaJMWCCALW19,
author = {Ye Jia and
Melvin Johnson and
Wolfgang Macherey and
Ron J. Weiss and
Yuan Cao and
Chung-Cheng Chiu and
Naveen Ari and
Stella Laurenzo and
Yonghui Wu},
title = {Leveraging Weakly Supervised Data to Improve End-to-end Speech-to-text
Translation},
pages = {7180--7184},
publisher = {IEEE Transactions on Acoustics, Speech, and Signal Processing},
year = {2019}
}
@inproceedings{DBLP:conf/interspeech/WuWPG20,
author = {Anne Wu and
Changhan Wang and
Juan Pino and
Jiatao Gu},
title = {Self-Supervised Representations Improve End-to-End Speech Translation},
pages = {1491--1495},
publisher = {International Symposium on Computer Architecture},
year = {2020}
}
@inproceedings{DBLP:conf/interspeech/LiuXZHWWZ19,
author = {Yuchen Liu and
Hao Xiong and
Jiajun Zhang and
Zhongjun He and
Hua Wu and
Haifeng Wang and
Chengqing Zong},
title = {End-to-End Speech Translation with Knowledge Distillation},
pages = {1128--1132},
publisher = {International Symposium on Computer Architecture},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/AlinejadS20,
author = {Ashkan Alinejad and
Anoop Sarkar},
title = {Effectively pretraining a speech translation decoder with Machine
Translation data},
pages = {8014--8020},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@article{DBLP:journals/corr/abs-1802-06003,
author = {Takatomo Kano and
Sakriani Sakti and
Satoshi Nakamura},
title = {Structured-based Curriculum Learning for End-to-end English-Japanese
Speech Translation},
journal = {CoRR},
volume = {abs/1802.06003},
year = {2018}
}
@inproceedings{DBLP:conf/acl/WangWLZY20,
author = {Chengyi Wang and
Yu Wu and
Shujie Liu and
Ming Zhou and
Zhenglu Yang},
title = {Curriculum Pre-training for End-to-End Speech Translation},
pages = {3728--3738},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@book{DBLP:books/daglib/0071550,
author = {Lawrence R. Rabiner and
Biing-Hwang Juang},
title = {Fundamentals of speech recognition},
series = {Prentice Hall signal processing series},
publisher = {Prentice Hall},
year = {1993}
}
@book{benesty2008automatic,
title={Automatic Speech Recognition: a Deep Learning Approach},
author={Dong Yu,Li Deng},
year={2008},
publisher={Springer}
}
@book{Huang2001SpokenLP,
title={Spoken Language Processing: A Guide to Theory, Algorithm and System Development},
author={Xuedong Huang and Alex Acero and Hsiao-Wuen Hon},
year={2001},
publisher={Prentice Hall PTR}
}
@book{Quatieri2001DiscreteTimeSS,
title={Discrete-Time Speech Signal Processing: Principles and Practice},
author={Thomas F. Quatieri},
year={2001},
publisher={Prentice Hall PTR}
}
@inproceedings{Oppenheim2001DiscretetimeSP,
title={Discrete-time Signal Processing},
author={Alan V. Oppenheim and Ronald W. Schafer},
year={2009},
publisher={Pearson}
}
@book{洪青阳2020语音识别原理与应用,
title={语音识别：原理与应用},
author={洪青阳,李琳},
publisher={电子工业出版社},
year={2020}
}
@book{陈果果2020语音识别实战,
title={Kaldi语音识别实战},
author={陈果果 and 都家宇 and 那兴宇 and 张俊博},
publisher={电子工业出版社},
year={2020}
}
%%%%%%%%%%%%%%%%%王屹超部分，孟霞加%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
@inproceedings{DBLP:conf/mm/LinMSYYGZL20,
author = {Huan Lin and
Fandong Meng and
Jinsong Su and
Yongjing Yin and
Zhengyuan Yang and
Yubin Ge and
Jie Zhou and
Jiebo Luo},
title = {Dynamic Context-guided Capsule Network for Multimodal Machine Translation},
pages = {1320--1329},
publisher = { ACM Multimedia},
year = {2020}
}
@inproceedings{DBLP:conf/wmt/SpeciaFSE16,
author = {Lucia Specia and
Stella Frank and
Khalil Sima'an and
Desmond Elliott},
title = {A Shared Task on Multimodal Machine Translation and Crosslingual Image
Description},
pages = {543--553},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/wmt/ElliottFBBS17,
author = {Desmond Elliott and
Stella Frank and
Lo{\"{\i}}c Barrault and
Fethi Bougares and
Lucia Specia},
title = {Findings of the Second Shared Task on Multimodal Machine Translation
and Multilingual Image Description},
pages = {215--233},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/wmt/BarraultBSLEF18,
author = {Lo{\"{\i}}c Barrault and
Fethi Bougares and
Lucia Specia and
Chiraag Lala and
Desmond Elliott and
Stella Frank},
title = {Findings of the Third Shared Task on Multimodal Machine Translation},
pages = {304--323},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/wmt/CaglayanABGBBMH17,
author = {Ozan Caglayan and
Walid Aransa and
Adrien Bardet and
Mercedes Garc{\'{\i}}a-Mart{\'{\i}}nez and
Fethi Bougares and
Lo{\"{\i}}c Barrault and
Marc Masana and
Luis Herranz and
Joost van de Weijer},
title = {{LIUM-CVC} Submissions for {WMT17} Multimodal Translation Task},
pages = {432--439},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/wmt/LibovickyHTBP16,
author = {Jindrich Libovick{\'{y}} and
Jindrich Helcl and
Marek Tlust{\'{y}} and
Ondrej Bojar and
Pavel Pecina},
title = {{CUNI} System for {WMT16} Automatic Post-Editing and Multimodal Translation
Tasks},
pages = {646--654},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:conf/emnlp/CalixtoL17,
author = {Iacer Calixto and
Qun Liu},
title = {Incorporating Global Visual Features into Attention-based Neural Machine
Translation},
pages = {992--1003},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/wmt/HuangLSOD16,
author = {Po-Yao Huang and
Frederick Liu and
Sz-Rung Shiang and
Jean Oh and
Chris Dyer},
title = {Attention-based Multimodal Neural Machine Translation},
pages = {639--645},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@article{Elliott2015MultilingualID,
title={Multilingual Image Description with Neural Sequence Models},
author={Desmond Elliott and
Stella Frank and
Eva Hasler},
journal={arXiv: Computation and Language},
year={2015}
}
@inproceedings{DBLP:conf/wmt/MadhyasthaWS17,
author = {Pranava Swaroop Madhyastha and
Josiah Wang and
Lucia Specia},
title = {Sheffield MultiMT: Using Object Posterior Predictions for Multimodal
Machine Translation},
pages = {470--476},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@article{DBLP:journals/corr/CaglayanBB16,
author = {Ozan Caglayan and
Lo{\"{\i}}c Barrault and
Fethi Bougares},
title = {Multimodal Attention for Neural Machine Translation},
journal = {CoRR},
volume = {abs/1609.03976},
year = {2016}
}
@inproceedings{DBLP:conf/acl/CalixtoLC17,
author = {Iacer Calixto and
Qun Liu and
Nick Campbell},
title = {Doubly-Attentive Decoder for Multi-modal Neural Machine Translation},
pages = {1913--1924},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@article{DBLP:journals/corr/DelbrouckD17,
author = {Jean-Benoit Delbrouck and
St{\'{e}}phane Dupont},
title = {Multimodal Compact Bilinear Pooling for Multimodal Neural Machine
Translation},
journal = {CoRR},
volume = {abs/1703.08084},
year = {2017}
}
@inproceedings{DBLP:conf/acl/LibovickyH17,
author = {Jindrich Libovick{\'{y}} and
Jindrich Helcl},
title = {Attention Strategies for Multi-Source Sequence-to-Sequence Learning},
pages = {196--202},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@article{DBLP:journals/corr/abs-1712-03449,
author = {Jean-Benoit Delbrouck and
St{\'{e}}phane Dupont},
title = {Modulating and attending the source image during encoding improves
Multimodal Translation},
journal = {CoRR},
volume = {abs/1712.03449},
year = {2017}
}
@article{DBLP:journals/corr/abs-1807-11605,
author = {Hasan Sait Arslan and
Mark Fishel and
Gholamreza Anbarjafari},
title = {Doubly Attentive Transformer Machine Translation},
journal = {CoRR},
volume = {abs/1807.11605},
year = {2018}
}
@inproceedings{DBLP:conf/wmt/HelclLV18,
author = {Jindrich Helcl and
Jindrich Libovick{\'{y}} and
Dusan Varis},
title = {{CUNI} System for the {WMT18} Multimodal Translation Task},
pages = {616--623},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/ijcnlp/ElliottK17,
author = {Desmond Elliott and
{\'{A}}kos K{\'{a}}d{\'{a}}r},
title = {Imagination Improves Multimodal Translation},
pages = {130--141},
publisher = {International Joint Conference on Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/ZhouCLY18,
author = {Mingyang Zhou and
Runxiang Cheng and
Yong Jae Lee and
Zhou Yu},
title = {A Visual Attention Grounding Neural Model for Multimodal Machine Translation},
pages = {3643--3653},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2018}
}
@inproceedings{DBLP:conf/acl/CalixtoRA19,
author = {Iacer Calixto and
Miguel Rios and
Wilker Aziz},
title = {Latent Variable Model for Multi-modal Translation},
pages = {6392--6405},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/acl/YinMSZYZL20,
author = {Yongjing Yin and
Fandong Meng and
Jinsong Su and
Chulun Zhou and
Zhengyuan Yang and
Jie Zhou and
Jiebo Luo},
title = {A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine
Translation},
pages = {3025--3035},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/acl/YaoW20,
author = {Shaowei Yao and
Xiaojun Wan},
title = {Multimodal Transformer for Multimodal Machine Translation},
pages = {4346--4350},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/nips/LuYBP16,
author = {Jiasen Lu and
Jianwei Yang and
Dhruv Batra and
Devi Parikh},
title = {Hierarchical Question-Image Co-Attention for Visual Question Answering},
booktitle = {Conference on Neural Information Processing Systems},
pages = {289--297},
year = {2016}
}
@inproceedings{DBLP:conf/cvpr/VinyalsTBE15,
author = {Oriol Vinyals and
Alexander Toshev and
Samy Bengio and
Dumitru Erhan},
title = {Show and tell: {A} neural image caption generator},
pages = {3156--3164},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2015}
}
@inproceedings{DBLP:conf/icml/XuBKCCSZB15,
author = {Kelvin Xu and
Jimmy Ba and
Ryan Kiros and
Kyunghyun Cho and
Aaron C. Courville and
Ruslan Salakhutdinov and
Richard S. Zemel and
Yoshua Bengio},
title = {Show, Attend and Tell: Neural Image Caption Generation with Visual
Attention},
volume = {37},
pages = {2048--2057},
publisher = {International Conference on Machine Learning},
year = {2015}
}
@inproceedings{DBLP:conf/cvpr/YouJWFL16,
author = {Quanzeng You and
Hailin Jin and
Zhaowen Wang and
Chen Fang and
Jiebo Luo},
title = {Image Captioning with Semantic Attention},
pages = {4651--4659},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2016}
}
@inproceedings{DBLP:conf/cvpr/ChenZXNSLC17,
author = {Long Chen and
Hanwang Zhang and
Jun Xiao and
Liqiang Nie and
Jian Shao and
Wei Liu and
Tat-Seng Chua},
title = {{SCA-CNN:} Spatial and Channel-Wise Attention in Convolutional Networks
for Image Captioning},
pages = {6298--6306},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2017}
}
@article{DBLP:journals/pami/FuJCSZ17,
author = {Kun Fu and
Junqi Jin and
Runpeng Cui and
Fei Sha and
Changshui Zhang},
title = {Aligning Where to See and What to Tell: Image Captioning with Region-Based
Attention and Scene-Specific Contexts},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume = {39},
number = {12},
pages = {2321--2334},
year = {2017}
}
@inproceedings{DBLP:conf/eccv/YaoPLM18,
author = {Ting Yao and
Yingwei Pan and
Yehao Li and
Tao Mei},
title = {Exploring Visual Relationship for Image Captioning},
series = {Lecture Notes in Computer Science},
volume = {11218},
pages = {711--727},
publisher = {European Conference on Computer Vision},
year = {2018}
}
@inproceedings{DBLP:conf/ijcai/LiuSWWY17,
author = {Chang Liu and
Fuchun Sun and
Changhu Wang and
Feng Wang and
Alan L. Yuille},
title = {{MAT:} {A} Multimodal Attentive Translator for Image Captioning},
pages = {4033--4039},
publisher = {International Joint Conference on Artificial Intelligence},
year = {2017}
}
@article{DBLP:journals/corr/abs-1804-02767,
author = {Joseph Redmon and
Ali Farhadi},
title = {YOLOv3: An Incremental Improvement},
journal = {CoRR},
volume = {abs/1804.02767},
year = {2018}
}
@article{DBLP:journals/corr/abs-2004-10934,
author = {Alexey Bochkovskiy and
Chien-Yao Wang and
Hong-Yuan Mark Liao},
title = {YOLOv4: Optimal Speed and Accuracy of Object Detection},
journal = {CoRR},
volume = {abs/2004.10934},
year = {2020}
}
@inproceedings{DBLP:conf/cvpr/LuXPS17,
author = {Jiasen Lu and
Caiming Xiong and
Devi Parikh and
Richard Socher},
title = {Knowing When to Look: Adaptive Attention via a Visual Sentinel for
Image Captioning},
pages = {3242--3250},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2017}
}
@inproceedings{DBLP:conf/cvpr/00010BT0GZ18,
author = {Peter Anderson and
Xiaodong He and
Chris Buehler and
Damien Teney and
Mark Johnson and
Stephen Gould and
Lei Zhang},
title = {Bottom-Up and Top-Down Attention for Image Captioning and Visual Question
Answering},
pages = {6077--6086},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2018}
}
@inproceedings{DBLP:conf/mm/ZhouXKC17,
author = {Luowei Zhou and
Chenliang Xu and
Parker A. Koch and
Jason J. Corso},
title = {Watch What You Just Said: Image Captioning with Text-Conditional Attention},
pages = {305--313},
publisher = {ACM Multimedia},
year = {2017}
}
@article{DBLP:journals/mta/FangWCT18,
author = {Fang Fang and
Hanli Wang and
Yihao Chen and
Pengjie Tang},
title = {Looking deeper and transferring attention for image captioning},
journal = {Multimedia Tools Applications},
volume = {77},
number = {23},
pages = {31159--31175},
year = {2018}
}
@inproceedings{DBLP:conf/cvpr/AnejaDS18,
author = {Jyoti Aneja and
Aditya Deshpande and
Alexander G. Schwing},
title = {Convolutional Image Captioning},
pages = {5561--5570},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2018}
}
@article{DBLP:journals/corr/abs-1805-09019,
author = {Qingzhong Wang and
Antoni B. Chan},
title = {{CNN+CNN:} Convolutional Decoders for Image Captioning},
journal = {CoRR},
volume = {abs/1805.09019},
year = {2018}
}
@inproceedings{DBLP:conf/eccv/DaiYL18,
author = {Bo Dai and
Deming Ye and
Dahua Lin},
title = {Rethinking the Form of Latent States in Image Captioning},
volume = {11209},
pages = {294--310},
publisher = {European Conference on Computer Vision},
year = {2018}
}
@inproceedings{DBLP:conf/iccv/AntolALMBZP15,
author = {Stanislaw Antol and
Aishwarya Agrawal and
Jiasen Lu and
Margaret Mitchell and
Dhruv Batra and
C. Lawrence Zitnick and
Devi Parikh},
title = {{VQA:} Visual Question Answering},
pages = {2425--2433},
publisher = {International Conference on Computer Vision},
year = {2015}
}
@inproceedings{DBLP:conf/eccv/CarionMSUKZ20,
author = {Nicolas Carion and
Francisco Massa and
Gabriel Synnaeve and
Nicolas Usunier and
Alexander Kirillov and
Sergey Zagoruyko},
title = {End-to-End Object Detection with Transformers},
volume = {12346},
pages = {213--229},
publisher = {European Conference on Computer Vision},
year = {2020}
}
@article{DBLP:journals/tcsv/YuLYH20,
author = {Jun Yu and
Jing Li and
Zhou Yu and
Qingming Huang},
title = {Multimodal Transformer With Multi-View Visual Representation for Image
Captioning},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
volume = {30},
number = {12},
pages = {4467--4480},
year = {2020}
}
@article{Huasong2020SelfAdaptiveNM,
title={Self-Adaptive Neural Module Transformer for Visual Question Answering},
author={Zhong Huasong and Jingyuan Chen and Chen Shen and Hanwang Zhang and Jianqiang Huang and Xian-Sheng Hua},
journal={IEEE Transactions on Multimedia},
year={2020},
pages={1-1}
}
@inproceedings{DBLP:conf/emnlp/GokhaleBBY20,
author = {Tejas Gokhale and
Pratyay Banerjee and
Chitta Baral and
Yezhou Yang},
title = {{MUTANT:} {A} Training Paradigm for Out-of-Distribution Generalization
in Visual Question Answering},
pages = {878--892},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2020}
}
@inproceedings{DBLP:conf/eccv/Tang0ZWY20,
author = {Ruixue Tang and
Chao Ma and
Wei Emma Zhang and
Qi Wu and
Xiaokang Yang},
title = {Semantic Equivalent Adversarial Data Augmentation for Visual Question
Answering},
volume = {12364},
pages = {437--453},
publisher = { European Conference on Computer Vision},
year = {2020}
}
@inproceedings{DBLP:conf/eccv/Li0LZHZWH0WCG20,
author = {Xiujun Li and
Xi Yin and
Chunyuan Li and
Pengchuan Zhang and
Xiaowei Hu and
Lei Zhang and
Lijuan Wang and
Houdong Hu and
Li Dong and
Furu Wei and
Yejin Choi and
Jianfeng Gao},
title = {Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks},
volume = {12375},
pages = {121--137},
publisher = { European Conference on Computer Vision},
year = {2020}
}
@inproceedings{DBLP:conf/aaai/ZhouPZHCG20,
author = {Luowei Zhou and
Hamid Palangi and
Lei Zhang and
Houdong Hu and
Jason J. Corso and
Jianfeng Gao},
title = {Unified Vision-Language Pre-Training for Image Captioning and {VQA}},
pages = {13041--13049},
publisher = {AAAI Conference on Artificial Intelligence},
year = {2020}
}
@inproceedings{DBLP:conf/iclr/SuZCLLWD20,
author = {Weijie Su and
Xizhou Zhu and
Yue Cao and
Bin Li and
Lewei Lu and
Furu Wei and
Jifeng Dai},
title = {{VL-BERT:} Pre-training of Generic Visual-Linguistic Representations},
publisher = {International Conference on Learning Representations},
year = {2020}
}
@inproceedings{DBLP:conf/nips/GoodfellowPMXWOCB14,
author = {Ian J. Goodfellow and
Jean Pouget-Abadie and
Mehdi Mirza and
Bing Xu and
David Warde-Farley and
Sherjil Ozair and
Aaron C. Courville and
Yoshua Bengio},
title = {Generative Adversarial Nets},
publisher = {Conference on Neural Information Processing Systems},
pages = {2672--2680},
year = {2014}
}
@inproceedings{DBLP:conf/nips/ZhuZPDEWS17,
author = {Jun-Yan Zhu and
Richard Zhang and
Deepak Pathak and
Trevor Darrell and
Alexei A. Efros and
Oliver Wang and
Eli Shechtman},
title = {Toward Multimodal Image-to-Image Translation},
publisher = {Conference on Neural Information Processing Systems},
pages = {465--476},
year = {2017}
}
@article{DBLP:journals/corr/abs-1908-06616,
author = {Hajar Emami and
Majid Moradi Aliabadi and
Ming Dong and
Ratna Babu Chinnam},
title = {{SPA-GAN:} Spatial Attention {GAN} for Image-to-Image Translation},
journal = {CoRR},
volume = {abs/1908.06616},
year = {2019}
}
@article{DBLP:journals/access/XiongWG19,
author = {Feng Xiong and
Qianqian Wang and
Quanxue Gao},
title = {Consistent Embedded {GAN} for Image-to-Image Translation},
journal = {International Conference on Access Networks},
volume = {7},
pages = {126651--126661},
year = {2019}
}
@inproceedings{DBLP:conf/iccv/ZhuPIE17,
author = {Jun-Yan Zhu and
Taesung Park and
Phillip Isola and
Alexei A. Efros},
title = {Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial
Networks},
pages = {2242--2251},
publisher = {International Conference on Computer Vision},
year = {2017}
}
@inproceedings{DBLP:conf/iccv/YiZTG17,
author = {Zili Yi and
Hao (Richard) Zhang and
Ping Tan and
Minglun Gong},
title = {DualGAN: Unsupervised Dual Learning for Image-to-Image Translation},
pages = {2868--2876},
publisher = {International Conference on Computer Vision},
year = {2017}
}
@inproceedings{DBLP:conf/nips/LiuBK17,
author = {Ming-Yu Liu and
Thomas Breuel and
Jan Kautz},
title = {Unsupervised Image-to-Image Translation Networks},
publisher = {Conference on Neural Information Processing Systems},
pages = {700--708},
year = {2017}
}
@inproceedings{DBLP:conf/cvpr/IsolaZZE17,
author = {Phillip Isola and
Jun-Yan Zhu and
Tinghui Zhou and
Alexei A. Efros},
title = {Image-to-Image Translation with Conditional Adversarial Networks},
pages = {5967--5976},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2017}
}
@inproceedings{DBLP:conf/icml/ReedAYLSL16,
author = {Scott E. Reed and
Zeynep Akata and
Xinchen Yan and
Lajanugen Logeswaran and
Bernt Schiele and
Honglak Lee},
title = {Generative Adversarial Text to Image Synthesis},
volume = {48},
pages = {1060--1069},
publisher = {International Conference on Machine Learning},
year = {2016}
}
@article{DBLP:journals/corr/DashGALA17,
author = {Ayushman Dash and
John Cristian Borges Gamboa and
Sheraz Ahmed and
Marcus Liwicki and
Muhammad Zeshan Afzal},
title = {{TAC-GAN} - Text Conditioned Auxiliary Classifier Generative Adversarial
Network},
journal = {CoRR},
volume = {abs/1703.06412},
year = {2017}
}
@inproceedings{DBLP:conf/nips/ReedAMTSL16,
author = {Scott E. Reed and
Zeynep Akata and
Santosh Mohan and
Samuel Tenka and
Bernt Schiele and
Honglak Lee},
title = {Learning What and Where to Draw},
publisher = {Conference on Neural Information Processing Systems},
pages = {217--225},
year = {2016}
}
@inproceedings{DBLP:conf/cvpr/ZhangXY18,
author = {Zizhao Zhang and
Yuanpu Xie and
Lin Yang},
title = {Photographic Text-to-Image Synthesis With a Hierarchically-Nested
Adversarial Network},
pages = {6199--6208},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2018}
}
@inproceedings{DBLP:conf/acl/MaHXZLZZHLLWW19,
author = {Mingbo Ma and
Liang Huang and
Hao Xiong and
Renjie Zheng and
Kaibo Liu and
Baigong Zheng and
Chuanqiang Zhang and
Zhongjun He and
Hairong Liu and
Xing Li and
Hua Wu and
Haifeng Wang},
title = {{STACL:} Simultaneous Translation with Implicit Anticipation and Controllable
Latency using Prefix-to-Prefix Framework},
pages = {3025--3036},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/ZhengMZH19,
author = {Renjie Zheng and
Mingbo Ma and
Baigong Zheng and
Liang Huang},
title = {Speculative Beam Search for Simultaneous Translation},
pages = {1395--1402},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:conf/naacl/DalviDSV18,
author = {Fahim Dalvi and
Nadir Durrani and
Hassan Sajjad and
Stephan Vogel},
title = {Incremental Decoding and Training Methods for Simultaneous Translation
in Neural Machine Translation},
pages = {493--499},
publisher = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year = {2018}
}
@article{DBLP:journals/corr/ChoE16,
author = {Kyunghyun Cho and
Masha Esipova},
title = {Can neural machine translation do simultaneous translation?},
journal = {CoRR},
volume = {abs/1606.02012},
year = {2016}
}
@inproceedings{DBLP:conf/eacl/NeubigCGL17,
author = {Jiatao Gu and
Graham Neubig and
Kyunghyun Cho and
Victor O. K. Li},
title = {Learning to Translate in Real-time with Neural Machine Translation},
pages = {1053--1062},
publisher = {Annual Conference of the European Association for Machine Translation},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/GrissomHBMD14,
author = {Alvin Grissom II and
He He and
Jordan L. Boyd-Graber and
John Morgan and
Hal Daum{\'{e}} III},
title = {Don't Until the Final Verb Wait: Reinforcement Learning for Simultaneous
Machine Translation},
pages = {1342--1352},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2014}
}
@inproceedings{DBLP:conf/acl/ZhengLZMLH20,
author = {Baigong Zheng and
Kaibo Liu and
Renjie Zheng and
Mingbo Ma and
Hairong Liu and
Liang Huang},
title = {Simultaneous Translation Policies: From Fixed to Adaptive},
pages = {2847--2853},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020}
}
@inproceedings{DBLP:conf/emnlp/ZhengZMH19,
author = {Baigong Zheng and
Renjie Zheng and
Mingbo Ma and
Liang Huang},
title = {Simpler and Faster Learning of Adaptive Policies for Simultaneous
Translation},
pages = {1349--1354},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:conf/acl/ZhengZMH19,
author = {Baigong Zheng and
Renjie Zheng and
Mingbo Ma and
Liang Huang},
title = {Simultaneous Translation with Flexible Policy via Restricted Imitation
Learning},
pages = {5816--5822},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2019}
}
@inproceedings{DBLP:conf/acl/ArivazhaganCMCY19,
author = {Naveen Arivazhagan and
Colin Cherry and
Wolfgang Macherey and
Chung-Cheng Chiu and
Semih Yavuz and
Ruoming Pang and
Wei Li and
Colin Raffel},
title = {Monotonic Infinite Lookback Attention for Simultaneous Machine Translation},
pages = {1313--1323},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
%%%%% chapter 17------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%cha
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 18------------------------------------------------------
@inproceedings{DBLP:conf/aaai/XiaHLS19,
author = {Mengzhou Xia and
Guoping Huang and
Lemao Liu and
Shuming Shi},
title = {Graph Based Translation Memory for Neural Machine Translation},
pages = {7297--7304},
publisher = {the Association for the Advance of Artificial Intelligence},
year = {2019}
}
@inproceedings{DBLP:conf/acl/WangZS13,
author = {Kun Wang and
Chengqing Zong and
Keh-Yih Su},
title = {Integrating Translation Memory into Phrase-Based Machine Translation
during Decoding},
pages = {11--21},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@inproceedings{DBLP:conf/acl/DomingoGEBHPCH19,
author = {Miguel Domingo and
Mercedes Garc{\'{\i}}a-Mart{\'{\i}}nez and
Amando Estela and
Laurent Bi{\'{e}} and
Alexandre Helle and
{\'{A}}lvaro Peris and
Francisco Casacuberta and
Manuel Herranz},
title = {Demonstration of a Neural Machine Translation System with Online Learning
for Translators},
pages = {70--74},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/emnlp/NguyenDB17,
author = {Khanh Nguyen and
Hal Daum{\'{e}} III and
Jordan L. Boyd-Graber},
title = {Reinforcement Learning for Bandit Neural Machine Translation with
Simulated Human Feedback},
pages = {1464--1474},
publisher = {Empirical Methods in Natural Language Processing},
year = {2017}
}
@inproceedings{DBLP:journals/corr/abs-1805-01553,
author = {Tsz Kin Lam and
Julia Kreutzer and
Stefan Riezler},
title = {A Reinforcement Learning Approach to Interactive-Predictive Neural
Machine Translation},
publisher = {CoRR},
volume = {abs/1805.01553},
year = {2018}
}
@inproceedings{DBLP:journals/mt/DomingoPC17,
author = {Miguel Domingo and
{\'{A}}lvaro Peris and
Francisco Casacuberta},
title = {Segment-based interactive-predictive machine translation},
publisher = {Machine Translation},
volume = {31},
number = {4},
pages = {163--185},
year = {2017}
}
@inproceedings{Peris2017InteractiveNM,
title={Interactive neural machine translation},
author={{\'A}lvaro Peris and Miguel Domingo and F. Casacuberta},
publisher={Computer Speech and Language},
year={2017},
volume={45},
pages={201-220}
}
@inproceedings{DBLP:journals/csl/PerisC19,
author = {{\'{A}}lvaro Peris and
Francisco Casacuberta},
title = {Online learning for effort reduction in interactive neural machine
translation},
publisher = {Computer Speech Language},
volume = {58},
pages = {98--126},
year = {2019}
}
@inproceedings{DBLP:journals/coling/BarrachinaBCCCKLNTVV09,
author = {Sergio Barrachina and
Oliver Bender and
Francisco Casacuberta and
Jorge Civera and
Elsa Cubel and
Shahram Khadivi and
Antonio L. Lagarda and
Hermann Ney and
Jes{\'{u}}s Tom{\'{a}}s and
Enrique Vidal and
Juan Miguel Vilar},
title = {Statistical Approaches to Computer-Assisted Translation},
publisher = {Computer Linguistics},
volume = {35},
number = {1},
pages = {3--28},
year = {2009}
}
@inproceedings{Zens2003EfficientSF,
title={Efficient Search for Interactive Statistical Machine Translation},
author={Franz Josef Och and Richard Zens and Hermann Ney},
booktitle={the European Chapter of the Association for Computational Linguistics},
year={2003},
pages = {387--393}
}
@inproceedings{DBLP:conf/acl/WuebkerGDHL16,
author = {Joern Wuebker and
Spence Green and
John DeNero and
Sasa Hasan and
Minh-Thang Luong},
title = {Models and Inference for Prefix-Constrained Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{DBLP:journals/corr/abs-2010-05680,
author = {Jiarui Fang and
Yang Yu and
Chengduo Zhao and
Jie Zhou},
title = {TurboTransformers: An Efficient {GPU} Serving System For Transformer
Models},
publisher = {CoRR},
volume = {abs/2010.05680},
year = {2020}
}
@inproceedings{DBLP:conf/iclr/HuangCLWMW18,
author = {Gao Huang and
Danlu Chen and
Tianhong Li and
Felix Wu and
Laurens van der Maaten and
Kilian Q. Weinberger},
title = {Multi-Scale Dense Networks for Resource Efficient Image Classification},
publisher = {International Conference on Learning Representations},
year = {2018}
}
@inproceedings{DBLP:journals/corr/BolukbasiWDS17,
author = {Tolga Bolukbasi and
Joseph Wang and
Ofer Dekel and
Venkatesh Saligrama},
title = {Adaptive Neural Networks for Fast Test-Time Prediction},
publisher = {CoRR},
volume = {abs/1702.07811},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/WangXZ20,
author = {Qiang Wang and
Tong Xiao and
Jingbo Zhu},
title = {Training Flexible Depth Model by Multi-Task Learning for Neural Machine
Translation},
pages = {4307--4312},
publisher = {Conference on Empirical Methods in Natural Language Processing},
year = {2020}
}
@inproceedings{DBLP:conf/ijcai/ChenCWL20,
author = {Guanhua Chen and
Yun Chen and
Yong Wang and
Victor O. K. Li},
title = {Lexical-Constraint-Aware Neural Machine Translation via Data Augmentation},
pages = {3587--3593},
publisher = {International Joint Conference on Artificial Intelligence},
year = {2020}
}
@inproceedings{DBLP:journals/corr/abs-1912-00567,
author = {Tao Wang and
Shaohui Kuang and
Deyi Xiong and
Ant{\'{o}}nio Branco},
title = {Merging External Bilingual Pairs into Neural Machine Translation},
publisher = {CoRR},
volume = {abs/1912.00567},
year = {2019}
}
@inproceedings{DBLP:conf/acl/DinuMFA19,
author = {Georgiana Dinu and
Prashant Mathur and
Marcello Federico and
Yaser Al-Onaizan},
title = {Training Neural Machine Translation to Apply Terminology Constraints},
pages = {3063--3068},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/naacl/SongZYLWZ19,
author = {Kai Song and
Yue Zhang and
Heng Yu and
Weihua Luo and
Kun Wang and
Min Zhang},
title = {Code-Switching for Enhancing {NMT} with Pre-Specified Translation},
pages = {449--459},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/naacl/HaslerGIB18,
author = {Eva Hasler and
Adri{\`{a}} de Gispert and
Gonzalo Iglesias and
Bill Byrne},
title = {Neural Machine Translation Decoding with Terminology Constraints},
pages = {506--512},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/wmt/ChatterjeeNTFSB17,
author = {Rajen Chatterjee and
Matteo Negri and
Marco Turchi and
Marcello Federico and
Lucia Specia and
Fr{\'{e}}d{\'{e}}ric Blain},
title = {Guiding Neural Machine Translation Decoding with External Knowledge},
pages = {157--168},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/naacl/PostV18,
author = {Matt Post and
David Vilar},
title = {Fast Lexically Constrained Decoding with Dynamic Beam Allocation for
Neural Machine Translation},
pages = {1314--1324},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:conf/acl/HokampL17,
author = {Chris Hokamp and
Qun Liu},
title = {Lexically Constrained Decoding for Sequence Generation Using Grid
Beam Search},
pages = {1535--1546},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/naacl/ThompsonGKDK19,
author = {Brian Thompson and
Jeremy Gwinnup and
Huda Khayrallah and
Kevin Duh and
Philipp Koehn},
title = {Overcoming Catastrophic Forgetting During Domain Adaptation of Neural
Machine Translation},
pages = {2062--2068},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{DBLP:conf/aclnmt/KhayrallahTDK18,
author = {Huda Khayrallah and
Brian Thompson and
Kevin Duh and
Philipp Koehn},
title = {Regularized Training Objective for Continued Training for Domain Adaptation
in Neural Machine Translation},
pages = {36--44},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{barone2017regularization,
title={Regularization techniques for fine-tuning in neural machine translation},
author={Barone, Antonio Valerio Miceli and Haddow, Barry and Germann, Ulrich and Sennrich, Rico},
publisher={arXiv preprint arXiv:1707.09920},
year={2017}
}
@inproceedings{DBLP:journals/corr/ChuDK17,
author = {Chenhui Chu and
Raj Dabre and
Sadao Kurohashi},
title = {An Empirical Comparison of Simple Domain Adaptation Methods for Neural
Machine Translation},
publisher = {CoRR},
volume = {abs/1701.03214},
year = {2017}
}
@inproceedings{DBLP:conf/coling/GuF20,
author = {Shuhao Gu and
Yang Feng},
title = {Investigating Catastrophic Forgetting During Continual Training for
Neural Machine Translation},
pages = {4315--4326},
publisher = {International Committee on Computational Linguistics},
year = {2020}
}
%%%%% chapter 18------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter appendix-A------------------------------------------------------
@inproceedings{Tong2012NiuTrans,
author = {Tong Xiao and
Jingbo Zhu and
Hao Zhang and
Qiang Li},
title = {NiuTrans: An Open Source Toolkit for Phrase-based and Syntax-based
Machine Translation},
pages = {19--24},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2012}
}
@inproceedings{Li2010Joshua,
author = {Zhifei Li and
Chris Callison-Burch and
Chris Dyer and
Sanjeev Khudanpur and
Lane Schwartz and
Wren N. G. Thornton and
Jonathan Weese and
Omar Zaidan},
title = {Joshua: An Open Source Toolkit for Parsing-Based Machine Translation},
pages = {135--139},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{iglesias2009hierarchical,
author = {Gonzalo Iglesias and
Adri{\`{a}} de Gispert and
Eduardo Rodr{\'{\i}}guez Banga and
William J. Byrne},
title = {Hierarchical Phrase-Based Translation with Weighted Finite State Transducers},
pages = {433--441},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2009}
}
@inproceedings{dyer2010cdec,
author = {Chris Dyer and
Adam Lopez and
Juri Ganitkevitch and
Jonathan Weese and
Ferhan T{\"{u}}re and
Phil Blunsom and
Hendra Setiawan and
Vladimir Eidelman and
Philip Resnik},
title = {cdec: {A} Decoder, Alignment, and Learning Framework for Finite-State
and Context-Free Translation Models},
pages = {7--12},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2010}
}
@inproceedings{Cer2010Phrasal,
author = {Daniel M. Cer and
Michel Galley and
Daniel Jurafsky and
Christopher D. Manning},
title = {Phrasal: {A} Statistical Machine Translation Toolkit for Exploring
New Model Features},
pages = {9--12},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2010}
}
@inproceedings{vilar2012jane,
title={Jane: an advanced freely available hierarchical machine translation toolkit},
author={Vilar, David and Stein, Daniel and Huck, Matthias and Ney, Hermann},
publisher={Machine Translation},
volume={26},
number={3},
pages={197--216},
year={2012}
}
@inproceedings{DBLP:conf/naacl/DyerCS13,
author = {Chris Dyer and
Victor Chahuneau and
Noah A. Smith},
title = {A Simple, Fast, and Effective Reparameterization of {IBM} Model 2},
pages = {644--648},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2013}
}
@inproceedings{al2016theano,
author = {Rami Al-Rfou and
Guillaume Alain and
Amjad Almahairi and
Christof Angerm{\"{u}}ller and
Dzmitry Bahdanau and
Nicolas Ballas and
Fr{\'{e}}d{\'{e}}ric Bastien and
Justin Bayer and
Anatoly Belikov and
Alexander Belopolsky and
Yoshua Bengio and
Arnaud Bergeron and
James Bergstra and
Valentin Bisson and
Josh Bleecher Snyder and
Nicolas Bouchard and
Nicolas Boulanger-Lewandowski and
Xavier Bouthillier and
Alexandre de Br{\'{e}}bisson and
Olivier Breuleux and
Pierre Luc Carrier and
Kyunghyun Cho and
Jan Chorowski and
Paul F. Christiano and
Tim Cooijmans and
Marc-Alexandre C{\^{o}}t{\'{e}} and
Myriam C{\^{o}}t{\'{e}} and
Aaron C. Courville and
Yann N. Dauphin and
Olivier Delalleau and
Julien Demouth and
Guillaume Desjardins and
Sander Dieleman and
Laurent Dinh and
Melanie Ducoffe and
Vincent Dumoulin and
Samira Ebrahimi Kahou and
Dumitru Erhan and
Ziye Fan and
Orhan Firat and
Mathieu Germain and
Xavier Glorot and
Ian J. Goodfellow and
Matthew Graham and
{\c{C}}aglar G{\"{u}}l{\c{c}}ehre and
Philippe Hamel and
Iban Harlouchet and
Jean-Philippe Heng and
Bal{\'{a}}zs Hidasi and
Sina Honari and
Arjun Jain and
S{\'{e}}bastien Jean and
Kai Jia and
Mikhail Korobov and
Vivek Kulkarni and
Alex Lamb and
Pascal Lamblin and
Eric Larsen and
C{\'{e}}sar Laurent and
Sean Lee and
Simon Lefran{\c{c}}ois and
Simon Lemieux and
Nicholas L{\'{e}}onard and
Zhouhan Lin and
Jesse A. Livezey and
Cory Lorenz and
Jeremiah Lowin and
Qianli Ma and
Pierre-Antoine Manzagol and
Olivier Mastropietro and
Robert McGibbon and
Roland Memisevic and
Bart van Merri{\"{e}}nboer and
Vincent Michalski and
Mehdi Mirza and
Alberto Orlandi and
Christopher Joseph Pal and
Razvan Pascanu and
Mohammad Pezeshki and
Colin Raffel and
Daniel Renshaw and
Matthew Rocklin and
Adriana Romero and
Markus Roth and
Peter Sadowski and
John Salvatier and
Fran{\c{c}}ois Savard and
Jan Schl{\"{u}}ter and
John Schulman and
Gabriel Schwartz and
Iulian Vlad Serban and
Dmitriy Serdyuk and
Samira Shabanian and
{\'{E}}tienne Simon and
Sigurd Spieckermann and
S. Ramana Subramanyam and
Jakub Sygnowski and
J{\'{e}}r{\'{e}}mie Tanguay and
Gijs van Tulder and
Joseph P. Turian and
Sebastian Urban and
Pascal Vincent and
Francesco Visin and
Harm de Vries and
David Warde-Farley and
Dustin J. Webb and
Matthew Willson and
Kelvin Xu and
Lijun Xue and
Li Yao and
Saizheng Zhang and
Ying Zhang},
title = {Theano: {A} Python framework for fast computation of mathematical
expressions},
publisher = {CoRR},
volume = {abs/1605.02688},
year = {2016}
}
@inproceedings{DBLP:journals/corr/SennrichFCBHHJL17,
author = {Rico Sennrich and
Orhan Firat and
Kyunghyun Cho and
Barry Haddow and
Alexandra Birch and
Julian Hitschler and
Marcin Junczys-Dowmunt and
Samuel L{\"{a}}ubli and
Antonio Valerio Miceli Barone and
Jozef Mokry and
Maria Nadejde},
title = {Nematus: a Toolkit for Neural Machine Translation},
publisher = {Annual Conference of the European Association for Machine Translation},
pages = {65--68},
year = {2017}
}
@inproceedings{Koehn2007Moses,
author = {Philipp Koehn and
Hieu Hoang and
Alexandra Birch and
Chris Callison-Burch and
Marcello Federico and
Nicola Bertoldi and
Brooke Cowan and
Wade Shen and
Christine Moran and
Richard Zens and
Chris Dyer and
Ondrej Bojar and
Alexandra Constantin and
Evan Herbst},
title = {Moses: Open Source Toolkit for Statistical Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{zollmann2007the,
author = {Andreas Zollmann and
Ashish Venugopal and
Matthias Paulik and
Stephan Vogel},
title = {The Syntax Augmented {MT} {(SAMT)} System at the Shared Task for the
2007 {ACL} Workshop on Statistical Machine Translation},
pages = {216--219},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2007}
}
@inproceedings{och2003systematic,
author = {Franz Josef Och and
Hermann Ney},
title = {A Systematic Comparison of Various Statistical Alignment Models},
publisher = {Computational Linguistics},
volume = {29},
number = {1},
pages = {19--51},
year = {2003}
}
@inproceedings{zoph2016simple,
author = {Barret Zoph and
Ashish Vaswani and
Jonathan May and
Kevin Knight},
title = {Simple, Fast Noise-Contrastive Estimation for Large {RNN} Vocabularies},
pages = {1217--1222},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{Ottfairseq,
author = {Myle Ott and
Sergey Edunov and
Alexei Baevski and
Angela Fan and
Sam Gross and
Nathan Ng and
David Grangier and
Michael Auli},
title = {fairseq: {A} Fast, Extensible Toolkit for Sequence Modeling},
pages = {48--53},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2019}
}
@inproceedings{Vaswani2018Tensor2TensorFN,
author = {Ashish Vaswani and
Samy Bengio and
Eugene Brevdo and
Fran{\c{c}}ois Chollet and
Aidan N. Gomez and
Stephan Gouws and
Llion Jones and
Lukasz Kaiser and
Nal Kalchbrenner and
Niki Parmar and
Ryan Sepassi and
Noam Shazeer and
Jakob Uszkoreit},
title = {Tensor2Tensor for Neural Machine Translation},
pages = {193--199},
publisher = {Association for Machine Translation in the Americas},
year = {2018}
}
@inproceedings{KleinOpenNMT,
author = {Guillaume Klein and
Yoon Kim and
Yuntian Deng and
Jean Senellart and
Alexander M. Rush},
title = {OpenNMT: Open-Source Toolkit for Neural Machine Translation},
pages = {67--72},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2017}
}
@inproceedings{luong2016acl_hybrid,
author = {Minh-Thang Luong and
Christopher D. Manning},
title = {Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character
Models},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016}
}
@inproceedings{ZhangTHUMT,
author = {Jiacheng Zhang and
Yanzhuo Ding and
Shiqi Shen and
Yong Cheng and
Maosong Sun and
Huan-Bo Luan and
Yang Liu},
title = {{THUMT:} An Open Source Toolkit for Neural Machine Translation},
publisher = {CoRR},
volume = {abs/1706.06415},
year = {2017}
}
@inproceedings{JunczysMarian,
author = {Marcin Junczys-Dowmunt and
Roman Grundkiewicz and
Tomasz Dwojak and
Hieu Hoang and
Kenneth Heafield and
Tom Neckermann and
Frank Seide and
Ulrich Germann and
Alham Fikri Aji and
Nikolay Bogoychev and
Andr{\'{e}} F. T. Martins and
Alexandra Birch},
title = {Marian: Fast Neural Machine Translation in {C++}},
pages = {116--121},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{hieber2017sockeye,
author = {Felix Hieber and
Tobias Domhan and
Michael Denkowski and
David Vilar and
Artem Sokolov and
Ann Clifton and
Matt Post},
title = {Sockeye: {A} Toolkit for Neural Machine Translation},
publisher = {CoRR},
volume = {abs/1712.05690},
year = {2017}
}
@inproceedings{WangCytonMT,
author = {Xiaolin Wang and
Masao Utiyama and
Eiichiro Sumita},
title = {CytonMT: an Efficient Neural Machine Translation Open-source Toolkit
Implemented in {C++}},
pages = {133--138},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018}
}
@inproceedings{DBLP:journals/corr/abs-1805-10387,
author = {Oleksii Kuchaiev and
Boris Ginsburg and
Igor Gitman and
Vitaly Lavrukhin and
Carl Case and
Paulius Micikevicius},
title = {OpenSeq2Seq: extensible toolkit for distributed and mixed precision
training of sequence-to-sequence models},
publisher = {CoRR},
volume = {abs/1805.10387},
year = {2018}
}
@inproceedings{nmtpy2017,
author = {Ozan Caglayan and
Mercedes Garc{\'{\i}}a-Mart{\'{\i}}nez and
Adrien Bardet and
Walid Aransa and
Fethi Bougares and
Lo{\"{\i}}c Barrault},
title = {{NMTPY:} {A} Flexible Toolkit for Advanced Neural Machine Translation
Systems},
publisher = {The Prague Bulletin of Mathematical Linguistics},
volume = {109},
pages = {15--28},
year = {2017}
}
%%%%% chapter appendix-A------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%