bibliography.bib

% !Mode:: "TeX:UTF-8"
% !TEX encoding = UTF-8 Unicode

@article{nagao1984framework,
  title={A framework of a mechanical translation between Japanese and English by analogy principle},
  author={Nagao, Makoto},
  journal={Artificial and human intelligence},
  pages={351--354},
  year={1984}
}

@article{brown1990statistical,
  title={A statistical approach to machine translation},
  author={Brown, Peter F and Cocke, John and Della Pietra, Stephen A and Della Pietra, Vincent J and Jelinek, Frederick and Lafferty, John and Mercer, Robert L and Roossin, Paul S},
  journal={Computational linguistics},
  volume={16},
  number={2},
  pages={79--85},
  year={1990}
}

@inproceedings{koehn2003statistical,
  title={Statistical phrase-based translation},
  author={Koehn, Philipp and Och, Franz Josef and Marcu, Daniel},
  booktitle={Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology-Volume 1},
  pages={48--54},
  year={2003},
  organization={Association for Computational Linguistics}
}

@article{bahdanau2014neural,
  title={Neural machine translation by jointly learning to align and translate},
  author={Bahdanau, Dzmitry and Cho, Kyunghyun and Bengio, Yoshua},
  journal={arXiv preprint arXiv:1409.0473},
  year={2014}
}

@inproceedings{sutskever2014sequence,
  title={Sequence to sequence learning with neural networks},
  author={Sutskever, Ilya and Vinyals, Oriol and Le, Quoc V},
  booktitle={Advances in neural information processing systems},
  pages={3104--3112},
  year={2014}
}

@inproceedings{papineni2002bleu,
  title={BLEU: a method for automatic evaluation of machine translation},
  author={Papineni, Kishore and Roukos, Salim and Ward, Todd and Zhu, Wei-Jing},
  booktitle={Proceedings of the 40th annual meeting on association for computational linguistics},
  pages={311--318},
  year={2002},
  organization={Association for Computational Linguistics}
}

@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},
  booktitle={Proceedings of association for machine translation in the Americas},
  volume={200},
  number={6},
  year={2006}
}

@article{shiwen1993automatic,
  title={Automatic evaluation of output quality for machine translation systems},
  author={Shiwen, Yu},
  journal={Machine Translation},
  volume={8},
  number={1-2},
  pages={117--126},
  year={1993},
  publisher={Springer}
}
@article{rabiner1989tutorial,
  title={A tutorial on hidden Markov models and selected applications in speech recognition},
  author={Rabiner, Lawrence R},
  journal={Proceedings of the IEEE},
  volume={77},
  number={2},
  pages={257--286},
  year={1989},
  publisher={Ieee}
}

@article{rabiner1986introduction,
  title={An introduction to hidden Markov models},
  author={Rabiner, Lawrence and Juang, B},
  journal={ieee assp magazine},
  volume={3},
  number={1},
  pages={4--16},
  year={1986},
  publisher={IEEE}
}

@article{parsing2009speech,
  title={Speech and language processing},
  author={Parsing, Constituency},
  year={2009}
}

@article{ney1994structuring,
  title={On structuring probabilistic dependences in stochastic language modelling},
  author={Ney, Hermann and Essen, Ute and Kneser, Reinhard},
  journal={Computer Speech \& Language},
  volume={8},
  number={1},
  pages={1--38},
  year={1994}
}

@article{chen1999empirical,
  title={An empirical study of smoothing techniques for language modeling},
  author={Chen, Stanley F and Goodman, Joshua},
  journal={Computer Speech \& Language},
  volume={13},
  number={4},
  pages={359--394},
  year={1999},
  publisher={Elsevier}
}

@book{mao-prob-book-2011,
  title={概率论与数理统计教程: 第二版},
  author={茆诗松 and 程依明 and 濮晓龙 and 平装 and 查看清 and 单书目},
  year={2011},
  publisher={北京: 高等教育出版社}
}

@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}
}

@article{brown1993mathematics,
  title={The mathematics of statistical machine translation: Parameter estimation},
  author={Brown, Peter F and Pietra, Vincent J Della and Pietra, Stephen A Della and Mercer, Robert L},
  journal={Computational linguistics},
  volume={19},
  number={2},
  pages={263--311},
  year={1993},
  publisher={MIT Press}
}

@article{shannon1949communication,
  title={Communication theory of secrecy systems},
  author={Shannon, Claude E},
  journal={Bell system technical journal},
  volume={28},
  number={4},
  pages={656--715},
  year={1949},
  publisher={Wiley Online Library}
}

@book{liuke-markov-2004,
  title={实用马尔可夫决策过程},
  author={刘克},
  volume={3},
  year={2004},
  publisher={清华大学出版社}
}

@book{resnick1992adventures,
  title={Adventures in stochastic processes},
  author={Resnick, Sidney I},
  year={1992},
  publisher={Springer Science \& Business Media}
}

@article{good1953population,
  title={The population frequencies of species and the estimation of population parameters},
  author={Good, Irving J},
  journal={Biometrika},
  volume={40},
  number={3-4},
  pages={237--264},
  year={1953},
  publisher={Oxford University Press}
}

@article{gale1995good,
  title={Good-turing frequency estimation without tears},
  author={Gale, William A and Sampson, Geoffrey},
  journal={Journal of quantitative linguistics},
  volume={2},
  number={3},
  pages={217--237},
  year={1995},
  publisher={Taylor \& Francis}
}

@inproceedings{kneser1995improved,
  title={Improved backing-off for m-gram language modeling},
  author={Kneser, Reinhard and Ney, Hermann},
  booktitle={1995 International Conference on Acoustics, Speech, and Signal Processing},
  volume={1},
  pages={181--184},
  year={1995},
  organization={IEEE}
}

@article{chen1999empirical,
  title={An empirical study of smoothing techniques for language modeling},
  author={Chen, Stanley F and Goodman, Joshua},
  journal={Computer Speech \& Language},
  volume={13},
  number={4},
  pages={359--394},
  year={1999},
  publisher={Elsevier}
}
@book{chomsky2002syntactic,
  title={Syntactic structures},
  author={Chomsky, Noam},
  year={2002},
  publisher={Walter de Gruyter}
}

@article{shannon1948mathematical,
  title={A mathematical theory of communication},
  author={Shannon, Claude E},
  journal={Bell system technical journal},
  volume={27},
  number={3},
  pages={379--423},
  year={1948},
  publisher={Wiley Online Library}
}

@inproceedings{ng2002discriminative,
  title={On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes},
  author={Ng, Andrew Y and Jordan, Michael I},
  booktitle={Advances in neural information processing systems},
  pages={841--848},
  year={2002}
}

@article{lafferty2001conditional,
  title={Conditional random fields: Probabilistic models for segmenting and labeling sequence data},
  author={Lafferty, John and McCallum, Andrew and Pereira, Fernando CN},
  year={2001}
}

@article{huang2015bidirectional,
  title={Bidirectional LSTM-CRF models for sequence tagging},
  author={Huang, Zhiheng and Xu, Wei and Yu, Kai},
  journal={arXiv preprint arXiv:1508.01991},
  year={2015}
}

@article{ma2016end,
  title={End-to-end sequence labeling via bi-directional lstm-cnns-crf},
  author={Ma, Xuezhe and Hovy, Eduard},
  journal={arXiv preprint arXiv:1603.01354},
  year={2016}
}

@article{bengio2003neural,
  title={A neural probabilistic language model},
  author={Bengio, Yoshua and Ducharme, R{\'e}jean and Vincent, Pascal and Jauvin, Christian},
  journal={Journal of machine learning research},
  volume={3},
  number={Feb},
  pages={1137--1155},
  year={2003}
}

@inproceedings{mikolov2010recurrent,
  title={Recurrent neural network based language model},
  author={Mikolov, Tom{\'a}{\v{s}} and Karafi{\'a}t, Martin and Burget, Luk{\'a}{\v{s}} and {\v{C}}ernock{\`y}, Jan and Khudanpur, Sanjeev},
  booktitle={Eleventh annual conference of the international speech communication association},
  year={2010}
}

@inproceedings{chen2014fast,
  title={A fast and accurate dependency parser using neural networks},
  author={Chen, Danqi and Manning, Christopher D},
  booktitle={Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)},
  pages={740--750},
  year={2014}
}

@article{zhu2015long,
title={Long Short-Term Memory Over Tree Structures.},
author={Zhu, Xiaodan and Sobhani, Parinaz and Guo, Hongyu},
journal={arXiv: Computation and Language},
year={2015}
}

@book{aho1972theory,
  title={The theory of parsing, translation, and compiling},
  author={Aho, Alfred V and Ullman, Jeffrey D},
  volume={1},
  year={1972},
  publisher={Prentice-Hall Englewood Cliffs, NJ}
}

@inproceedings{huang2008advanced,
  title={Advanced Dynamic Programming in CL},
  author={Huang, Liang},
  year={2008}
}

@article{och2004alignment,
  title={The alignment template approach to statistical machine translation},
  author={Och, Franz Josef and Ney, Hermann},
  journal={Computational linguistics},
  volume={30},
  number={4},
  pages={417--449},
  year={2004},
  publisher={MIT Press}
}

@inproceedings{koehn2003statistical,
  title={Statistical phrase-based translation},
  author={Koehn, Philipp and Och, Franz Josef and Marcu, Daniel},
  booktitle={Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology-Volume 1},
  pages={48--54},
  year={2003},
  organization={Association for Computational Linguistics}
}

@article{och2003systematic,
  title={A systematic comparison of various statistical alignment models},
  author={Och, Franz Josef and Ney, Hermann},
  journal={Computational linguistics},
  volume={29},
  number={1},
  pages={19--51},
  year={2003},
  publisher={MIT Press}
}

@inproceedings{ittycheriah2005maximum,
  title={A maximum entropy word aligner for Arabic-English machine translation},
  author={Ittycheriah, Abraham and Roukos, Salim},
  booktitle={Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing},
  pages={89--96},
  year={2005},
  organization={Association for Computational Linguistics}
}

@article{xiao2013unsupervised,
  title={Unsupervised sub-tree alignment for tree-to-tree translation},
  author={Xiao, Tong and Zhu, Jingbo},
  journal={Journal of Artificial Intelligence Research},
  volume={48},
  pages={733--782},
  year={2013}
}
@inproceedings{vogel1996hmm,
  title={HMM-based word alignment in statistical translation},
  author={Vogel, Stephan and Ney, Hermann and Tillmann, Christoph},
  booktitle={Proceedings of the 16th conference on Computational linguistics-Volume 2},
  pages={836--841},
  year={1996},
  organization={Association for Computational Linguistics}
}

@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={MIT press}
}
@article{SPhilipp,
  title={Philipp Koehn, Statistical machine translation},
  author={Sánchez-Martínez, Felipe and Juan Antonio Pérez-Ortiz},
  volume={24},
  number={3-4},
  pages={273-278},
}

@article{SIDDHARTHANChristopher,
  title={Christopher D. Manning and Hinrich Schutze. Foundations of Statistical Natural Language Processing. MIT Press, 2000. ISBN 0-262-13360-1. 620 pp.},
  author={SIDDHARTHAN and ADVAITH},
  journal={Natural Language Engineering},
  volume={8},
  number={01},
}

@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},
}

@article{HeatonIan,
  title={Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep learning},
  author={Heaton and Jeff},
  journal={Genetic Programming \& Evolvable Machines},
  pages={s10710-017-9314-z},
}

@article{周志华2018《机器学习》,
  title={《机器学习》},
  author={周志华},
  journal={航空港},
  number={2},
  pages={94-94},
  year={2018},
}

@inproceedings{Tong2012NiuTrans,
  title={NiuTrans: an open source toolkit for phrase-based and syntax-based machine translation},
  author={Tong, Xiao and Zhu, Jingbo and Hao, Zhang and Qiang, Li},
  booktitle={Proceedings of the ACL 2012 System Demonstrations},
  year={2012},
}

@article{Koehn2007Moses,
  title={Moses: Open Source Toolkit for Statistical Machine Translation},
  author={Koehn, Philipp and Hoang, Hieu and Birch, Alexandra and Callisonburch, Chris and Federico, Marcello and Bertoldi, Nicola and Cowan, Brooke and Shen, Wade and Moran, Christine and Zens, Richard},
  volume={9},
  number={1},
  pages={177--180},
  year={2007},
}

@inproceedings{Dyer2010cdec,
  title={cdec: A Decoder, Alignment, and Learning Framework for Finite-State and Context-Free Translation Models},
  author={Dyer, Chris and Lopez, Adam and Ganitkevitch, Juri and Weese, Jonathan and Resnik, Philip},
  booktitle={ACL 2010, Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, July 11-16, 2010, Uppsala, Sweden, System Demonstrations},
  year={2010},
}

@article{SennrichNematus,
  title={Nematus: a Toolkit for Neural Machine Translation},
  author={Sennrich, Rico and Firat, Orhan and Cho, Kyunghyun and Birch, Alexandra and Haddow, Barry and Hitschler, Julian and Junczys-Dowmunt, Marcin and Läubli, Samuel and Barone, Antonio Valerio Miceli and Mokry, Jozef},
}

@article{Ottfairseq,
  title={fairseq: A Fast, Extensible Toolkit for Sequence Modeling},
  author={Ott, Myle and Edunov, Sergey and Baevski, Alexei and Fan, Angela and Gross, Sam and Ng, Nathan and Grangier, David and Auli, Michael},
}

@article{VaswaniTensor2Tensor,
  title={Tensor2Tensor for Neural Machine Translation},
  author={Vaswani, Ashish and Bengio, Samy and Brevdo, Eugene and Chollet, Francois and Gomez, Aidan N. and Gouws, Stephan and Jones, Llion and Kaiser, Łukasz and Kalchbrenner, Nal and Parmar, Niki},
}

@article{KleinOpenNMT,
  title={OpenNMT: Open-Source Toolkit for Neural Machine Translation},
  author={Klein, Guillaume and Kim, Yoon and Deng, Yuntian and Senellart, Jean and Rush, Alexander M.},
}

@article{ZhangTHUMT,
  title={THUMT: An Open Source Toolkit for Neural Machine Translation},
  author={Zhang, Jiacheng and Ding, Yanzhuo and Shen, Shiqi and Cheng, Yong and Sun, Maosong and Luan, Huanbo and Liu, Yang},
}

@article{WangCytonMT,
  title={CytonMT: an Efficient Neural Machine Translation Open-source Toolkit Implemented in C++},
  author={Wang, Xiaolin and Utiyama, Masao and Sumita, Eiichiro},
}

@article{Germann2016Modern,
  title={Modern MT: A New Open-Source Machine Translation Platform for the Translation Industry},
  author={Germann, Ulrich and Barbu, E and Bentivoglio, M and Bogoychev, Nikolay and Buck, C and Caroselli, D and Carvalho, L and Cattelan, A and Cattoni, R and Cettolo, M},
  year={2016},
 abstract={Modern MT (www.modernmt.eu) is a three-year Horizon 2020 innovation action(2015–2017) to develop new open-source machine translation technology for use in translation production environments, both fully automatic and as a back-end in interactive post-editing scenarios. Led by Translated srl, the project consortium also includes the Fondazione Bruno Kessler (FBK), the University of Edinburgh, and TAUS B.V. Modern MT has received funding from the European Union’s Horizon 2020 research and innovation programme under Grant Agreement No. 645487 (call ICT-17-2014).},
}

@article{JunczysMarian,
  title={Marian: Fast Neural Machine Translation in C++},
  author={Junczys-Dowmunt, Marcin and Grundkiewicz, Roman and Dwojak, Tomasz and Hoang, Hieu and Heafield, Kenneth and Neckermann, Tom and Seide, Frank and Germann, Ulrich and Aji, Alham Fikri and Bogoychev, Nikolay},
}

@article{hieber2017sockeye,
title={Sockeye: A Toolkit for Neural Machine Translation.},
author={Hieber, Felix and Domhan, Tobias and Denkowski, Michael and Vilar, David and Sokolov, Artem and Clifton, Ann and Post, Matt},
journal={arXiv: Computation and Language},
year={2017}}
    
@article{KuchaievMixed,
  title={Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq},
  author={Kuchaiev, Oleksii and Ginsburg, Boris and Gitman, Igor and Lavrukhin, Vitaly and Li, Jason and Nguyen, Huyen and Case, Carl and Micikevicius, Paulius},
}
    
@article{bahdanau2015neural,
title={Neural Machine Translation by Jointly Learning to Align and Translate},
author={Bahdanau, Dzmitry and Cho, Kyunghyun and Bengio, Yoshua},
year={2015}}

@article{Li2010Joshua,
  title={Joshua: An Open Source Toolkit for Parsing-based Machine Translation},
  author={Li, Zhifei and Callisonburch, Chris and Dyer, Chris and Ganitkevitch, Juri and Khudanpur, Sanjeev and Schwartz, Lane and Thornton, Wren N. G. and Weese, Jonathan and Zaidan, Omar F.},
  pages={135--139},
  year={2010},
}

@inproceedings{Goldberg2017Neural,
  title={Neural Network Methods in Natural Language Processing},
  author={Goldberg, Yoav and Hirst, Graeme},
  booktitle={Neural Network Methods in Natural Language Processing},
  year={2017},
}

@article{pino2010the,
title={The CUED HiFST System for the WMT10 Translation Shared Task},
author={Pino, Juan and Iglesias, Gonzalo and De Gispert, Adria and Blackwood, Graeme and Brunning, Jamie and Byrne, William},
pages={155--160},
year={2010}}
    
@book{Junczysdowmunt2012SyMGiza,
  title={SyMGiza++: Symmetrized Word Alignment Models for Statistical Machine Translation},
  author={Junczysdowmunt, Marcin and Szał, Arkadiusz},
  year={2012},
}

@article{VilarJane,
  title={Jane: an advanced freely available hierarchical machine translation toolkit},
  author={Vilar, David and Stein, Daniel and Huck, Matthias and Ney, Hermann},
  journal={Machine Translation},
  volume={26},
  number={3},
  pages={197-216},
}

@article{Cer2010Phrasal,
  title={Phrasal: A Statistical Machine Translation Toolkit for Exploring New Model Features.},
  author={Cer, Daniel M and Galley, Michel and Jurafsky, Daniel and Manning, Christopher D},
  year={2010},
}

@article{zollmann2007the,
title={The Syntax Augmented MT (SAMT) System at the Shared Task for the 2007 ACL Workshop on Statistical Machine Translation},
author={Zollmann, Andreas and Venugopal, Ashish and Paulik, Matthias and Vogel, Stephan},
pages={216--219},
year={2007}}

@article{曼宁2005《统计自然语言处理基础》,
  title={《统计自然语言处理基础》},
  author={曼宁},
  journal={中文信息学报},
  volume={19},
  number={3},
  pages={54-54},
  year={2005},
}

@article{zoph2016simple,
title={Simple, Fast Noise-Contrastive Estimation for Large RNN Vocabularies.},
author={Zoph, Barret and Vaswani, Ashish and May, Jonathan and Knight, Kevin},
pages={1217--1222},
year={2016}}

@article{dyer2013a,
title={A Simple, Fast, and Effective Reparameterization of IBM Model 2},
author={Dyer, Chris and Chahuneau, Victor and Smith, Noah A},
pages={644--648},
year={2013}}

@article{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},
  journal   = {Prague Bull. Math. Linguistics},
  volume    = {109},
  pages     = {15--28},
  year      = {2017},
  url       = {https://ufal.mff.cuni.cz/pbml/109/art-caglayan-et-al.pdf},
  doi       = {10.1515/pralin-2017-0035},
  timestamp = {Tue, 12 Sep 2017 10:01:08 +0100}
}

@inproceedings{luong2016acl_hybrid,
 author = {Luong, Minh-Thang  and  Manning, Christopher D.},
 title = {Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models},
 booktitle = {Association for Computational Linguistics (ACL)},
 address = {Berlin, Germany},
 month = {August},
 year = {2016}
}

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%section6

@article{DBLP:journals/corr/abs-1905-13324,
  author    = {Biao Zhang and
               Rico Sennrich},
  title     = {A Lightweight Recurrent Network for Sequence Modeling},
  journal   = {CoRR},
  volume    = {abs/1905.13324},
  year      = {2019},
  url       = {http://arxiv.org/abs/1905.13324},
  archivePrefix = {arXiv},
  eprint    = {1905.13324},
  timestamp = {Mon, 03 Jun 2019 13:42:33 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1905-13324.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{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 Gregory S. Corrado and Macduff Hughes and Jeffrey Dean},
  journal={ArXiv},
  year={2016},
  volume={abs/1609.08144}
}

@inproceedings{li-etal-2018-simple,
    title = "A Simple and Effective Approach to Coverage-Aware Neural Machine Translation",
    author = "Li, Yanyang  and
      Xiao, Tong  and
      Li, Yinqiao  and
      Wang, Qiang  and
      Xu, Changming  and
      Zhu, Jingbo",
    booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2018",
    address = "Melbourne, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/P18-2047",
    doi = "10.18653/v1/P18-2047",
    pages = "292--297",
    abstract = "We offer a simple and effective method to seek a better balance between model confidence and length preference for Neural Machine Translation (NMT). Unlike the popular length normalization and coverage models, our model does not require training nor reranking the limited n-best outputs. Moreover, it is robust to large beam sizes, which is not well studied in previous work. On the Chinese-English and English-German translation tasks, our approach yields +0.4 1.5 BLEU improvements over the state-of-the-art baselines.",
}

@article{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},
  journal   = {CoRR},
  volume    = {abs/1703.03130},
  year      = {2017},
  url       = {http://arxiv.org/abs/1703.03130},
  archivePrefix = {arXiv},
  eprint    = {1703.03130},
  timestamp = {Mon, 13 Aug 2018 16:46:06 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/LinFSYXZB17.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{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},
  journal   = {CoRR},
  volume    = {abs/1705.00753},
  year      = {2017},
  url       = {http://arxiv.org/abs/1705.00753},
  archivePrefix = {arXiv},
  eprint    = {1705.00753},
  timestamp = {Thu, 04 Jul 2019 16:25:18 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/ChenLCL17.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-1805-00631,
  author    = {Biao Zhang and
               Deyi Xiong and
               Jinsong Su},
  title     = {Accelerating Neural Transformer via an Average Attention Network},
  journal   = {CoRR},
  volume    = {abs/1805.00631},
  year      = {2018},
  url       = {http://arxiv.org/abs/1805.00631},
  archivePrefix = {arXiv},
  eprint    = {1805.00631},
  timestamp = {Mon, 13 Aug 2018 16:46:01 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1805-00631.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}@article{DBLP:journals/corr/abs-1805-00631,
  author    = {Biao Zhang and
               Deyi Xiong and
               Jinsong Su},
  title     = {Accelerating Neural Transformer via an Average Attention Network},
  journal   = {CoRR},
  volume    = {abs/1805.00631},
  year      = {2018},
  url       = {http://arxiv.org/abs/1805.00631},
  archivePrefix = {arXiv},
  eprint    = {1805.00631},
  timestamp = {Mon, 13 Aug 2018 16:46:01 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1805-00631.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{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},
  journal   = {CoRR},
  volume    = {abs/1602.02830},
  year      = {2016},
  url       = {http://arxiv.org/abs/1602.02830},
  archivePrefix = {arXiv},
  eprint    = {1602.02830},
  timestamp = {Mon, 13 Aug 2018 16:46:57 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/CourbariauxB16.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{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},
  journal   = {CoRR},
  volume    = {abs/1905.09418},
  year      = {2019},
  url       = {http://arxiv.org/abs/1905.09418},
  archivePrefix = {arXiv},
  eprint    = {1905.09418},
  timestamp = {Wed, 29 May 2019 11:27:50 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1905-09418.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

%//找不到，自己写的  层次短语翻译的神经网络调序模型
@incollection{liumodel,
title = {层次短语翻译的神经网络调序模型},
author = {李鹏,刘洋,孙茂松},
booktitle = {清华大学学报(自然科学版)},
pages = {1529-1533},
year = {2014}
}

@incollection{NIPS2017_7181,
title = {Attention is All you Need},
author = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, \L ukasz and Polosukhin, Illia},
booktitle = {Advances in Neural Information Processing Systems 30},
editor = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
pages = {5998--6008},
year = {2017},
publisher = {Curran Associates, Inc.},
url = {http://papers.nips.cc/paper/7181-attention-is-all-you-need.pdf}
}

@article{DBLP:journals/corr/ZhangZ16c,
  author    = {Jiajun Zhang and
               Chengqing Zong},
  title     = {Bridging Neural Machine Translation and Bilingual Dictionaries},
  journal   = {CoRR},
  volume    = {abs/1610.07272},
  year      = {2016},
  url       = {http://arxiv.org/abs/1610.07272},
  archivePrefix = {arXiv},
  eprint    = {1610.07272},
  timestamp = {Mon, 13 Aug 2018 16:47:14 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/ZhangZ16c.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/SeeLM16,
  author    = {Abigail See and
               Minh{-}Thang Luong and
               Christopher D. Manning},
  title     = {Compression of Neural Machine Translation Models via Pruning},
  journal   = {CoRR},
  volume    = {abs/1606.09274},
  year      = {2016},
  url       = {http://arxiv.org/abs/1606.09274},
  archivePrefix = {arXiv},
  eprint    = {1606.09274},
  timestamp = {Mon, 13 Aug 2018 16:48:35 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/SeeLM16.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{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},
  journal   = {CoRR},
  volume    = {abs/1805.10163},
  year      = {2018},
  url       = {http://arxiv.org/abs/1805.10163},
  archivePrefix = {arXiv},
  eprint    = {1805.10163},
  timestamp = {Mon, 13 Aug 2018 16:49:01 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1805-10163.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{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},
  journal   = {CoRR},
  volume    = {abs/1705.03122},
  year      = {2017},
  url       = {http://arxiv.org/abs/1705.03122},
  archivePrefix = {arXiv},
  eprint    = {1705.03122},
  timestamp = {Mon, 13 Aug 2018 16:48:03 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/GehringAGYD17.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{Ba2016LayerN,
  title={Layer Normalization},
  author={Jimmy Ba and Jamie Ryan Kiros and Geoffrey E. Hinton},
  journal={ArXiv},
  year={2016},
  volume={abs/1607.06450}
}

@article{DBLP:journals/corr/HeZRS15,
  author    = {Kaiming He and
               Xiangyu Zhang and
               Shaoqing Ren and
               Jian Sun},
  title     = {Deep Residual Learning for Image Recognition},
  journal   = {CoRR},
  volume    = {abs/1512.03385},
  year      = {2015},
  url       = {http://arxiv.org/abs/1512.03385},
  archivePrefix = {arXiv},
  eprint    = {1512.03385},
  timestamp = {Wed, 17 Apr 2019 17:23:45 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/HeZRS15.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{Hinton2015Distilling,
  title={Distilling the Knowledge in a Neural Network},
  author={Hinton, Geoffrey and Vinyals, Oriol and Dean, Jeff},
  journal={Computer Science},
  volume={14},
  number={7},
  pages={38-39},
  year={2015},
}

@InProceedings{pmlr-v9-glorot10a,
  title = 	 {Understanding the difficulty of training deep feedforward neural networks},
  author = 	 {Xavier Glorot and Yoshua Bengio},
  booktitle = 	 {Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics},
  pages = 	 {249--256},
  year = 	 {2010},
  editor = 	 {Yee Whye Teh and Mike Titterington},
  volume = 	 {9},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {Chia Laguna Resort, Sardinia, Italy},
  month = 	 {13--15 May},
  publisher = 	 {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v9/glorot10a/glorot10a.pdf},
  url = 	 {http://proceedings.mlr.press/v9/glorot10a.html},
  abstract = 	 {Whereas before 2006 it appears that deep multi-layer neural networks were not successfully trained, since then several algorithms have been shown to successfully train them, with experimental results showing the superiority of deeper vs less deep architectures. All these experimental results were obtained with new initialization or training mechanisms. Our objective here is to understand better why standard gradient descent from random initialization is doing so poorly with deep neural networks, to better understand these recent relative successes and help design better algorithms in the future.  We first observe the influence of the non-linear activations functions. We find that the logistic sigmoid activation is unsuited for deep networks with random initialization because of its mean value, which can drive especially the top hidden layer into saturation. Surprisingly, we find that saturated units can move out of saturation by themselves, albeit slowly, and explaining the plateaus sometimes seen when training neural networks. We find that a new non-linearity that saturates less can often be beneficial. Finally, we study how activations and gradients vary across layers and during training, with the idea that training may be more difficult when the singular values of the Jacobian associated with each layer are far from 1.  Based on these considerations, we propose a new initialization scheme that brings substantially faster convergence.}
}

@article{DBLP:journals/corr/LuongPM15,
  author    = {Minh{-}Thang Luong and
               Hieu Pham and
               Christopher D. Manning},
  title     = {Effective Approaches to Attention-based Neural Machine Translation},
  journal   = {CoRR},
  volume    = {abs/1508.04025},
  year      = {2015},
  url       = {http://arxiv.org/abs/1508.04025},
  archivePrefix = {arXiv},
  eprint    = {1508.04025},
  timestamp = {Mon, 13 Aug 2018 16:46:14 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/LuongPM15.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{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},
  journal   = {CoRR},
  volume    = {abs/1906.00532},
  year      = {2019},
  url       = {http://arxiv.org/abs/1906.00532},
  archivePrefix = {arXiv},
  eprint    = {1906.00532},
  timestamp = {Thu, 13 Jun 2019 13:36:00 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1906-00532.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@InProceedings{Liu_2019_CVPR,
author = {Liu, Shikun and Johns, Edward and Davison, Andrew J.},
title = {End-To-End Multi-Task Learning With Attention},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}

@article{MoradiInterrogating,
  title={Interrogating the Explanatory Power of Attention in Neural Machine Translation},
  author={Moradi, Pooya and Kambhatla, Nishant and Sarkar, Anoop},
}

@article{WangLearning,
  title={Learning Deep Transformer Models for Machine Translation},
  author={Wang, Qiang and Li, Bei and Xiao, Tong and Zhu, Jingbo and Li, Changliang and Wong, Derek F. and Chao, Lidia S.},
}

@article{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},
  journal = {Journal of Machine Learning Research},
  year    = {2014},
  volume  = {15},
  pages   = {1929-1958},
  url     = {http://jmlr.org/papers/v15/srivastava14a.html}
}

@InProceedings{Szegedy_2016_CVPR,
author = {Szegedy, Christian and Vanhoucke, Vincent and Ioffe, Sergey and Shlens, Jon and Wojna, Zbigniew},
title = {Rethinking the Inception Architecture for Computer Vision},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2016}
}

@article{BENGIO1994Learning,
  title={Learning Long-term Dependencies With Gradient Descent is Difficult},
  author={BENGIO,Y.},
  journal={IEEE Trans Neural Netw},
  volume={5},
  year={1994},
}

@article{Cho2014Learning,
  title={Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation},
  author={Cho, Kyunghyun and Van Merrienboer, Bart and Gulcehre, Caglar and Bahdanau, Dzmitry and Bougares, Fethi and Schwenk, Holger and Bengio, Yoshua},
  journal={Computer Science},
  year={2014},
}

@article{WangNeural,
  title={Neural Machine Translation Advised by Statistical Machine Translation},
  author={Wang, Xing and Lu, Zhengdong and Tu, Zhaopeng and Li, Hang and Xiong, Deyi and Zhang, Min},
}

@article{HochreiterLong,
  title={Long Short-Term Memory},
  author={Hochreiter, S and Schmidhuber, J},
  journal={Neural Computation},
  volume={9},
  number={8},
  pages={1735-1780},
}

@article{TuModeling,
  title={Modeling Coverage for Neural Machine Translation},
  author={Tu, Zhaopeng and Lu, Zhengdong and Liu, Yang and Liu, Xiaohua and Li, Hang},
}

@inproceedings{devlin-etal-2014-fast,
    title = "Fast and Robust Neural Network Joint Models for Statistical Machine Translation",
    author = "Devlin, Jacob  and
      Zbib, Rabih  and
      Huang, Zhongqiang  and
      Lamar, Thomas  and
      Schwartz, Richard  and
      Makhoul, John",
    booktitle = "Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jun,
    year = "2014",
    address = "Baltimore, Maryland",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/P14-1129",
    doi = "10.3115/v1/P14-1129",
    pages = "1370--1380",
}

@inproceedings{wang-etal-2018-multi-layer,
    title = "Multi-layer Representation Fusion for Neural Machine Translation",
    author = "Wang, Qiang  and
      Li, Fuxue  and
      Xiao, Tong  and
      Li, Yanyang  and
      Li, Yinqiao  and
      Zhu, Jingbo",
    booktitle = "Proceedings of the 27th International Conference on Computational Linguistics",
    month = aug,
    year = "2018",
    address = "Santa Fe, New Mexico, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/C18-1255",
    pages = "3015--3026",
    abstract = "Neural machine translation systems require a number of stacked layers for deep models. But the prediction depends on the sentence representation of the top-most layer with no access to low-level representations. This makes it more difficult to train the model and poses a risk of information loss to prediction. In this paper, we propose a multi-layer representation fusion (MLRF) approach to fusing stacked layers. In particular, we design three fusion functions to learn a better representation from the stack. Experimental results show that our approach yields improvements of 0.92 and 0.56 BLEU points over the strong Transformer baseline on IWSLT German-English and NIST Chinese-English MT tasks respectively. The result is new state-of-the-art in German-English translation.",
}

@article{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},
  journal   = {CoRR},
  volume    = {abs/1811.00498},
  year      = {2018},
  url       = {http://arxiv.org/abs/1811.00498},
  archivePrefix = {arXiv},
  eprint    = {1811.00498},
  timestamp = {Thu, 22 Nov 2018 17:58:30 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1811-00498.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{bahdanau2014neural,
  title={Neural machine translation by jointly learning to align and translate},
  author={Bahdanau, Dzmitry and Cho, Kyunghyun and Bengio, Yoshua},
  journal={arXiv preprint arXiv:1409.0473},
  year={2014}
}

@article{DBLP:journals/corr/SennrichFCBHHJL17,
  author    = {Rico Sennrich and
               Orhan Firat and
               Kyunghyun Cho and
               Alexandra Birch and
               Barry Haddow 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},
  journal   = {CoRR},
  volume    = {abs/1703.04357},
  year      = {2017},
  url       = {http://arxiv.org/abs/1703.04357},
  archivePrefix = {arXiv},
  eprint    = {1703.04357},
  timestamp = {Mon, 13 Aug 2018 16:46:45 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/SennrichFCBHHJL17.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{Li2020NeuralMT,
  title={Neural Machine Translation with Joint Representation},
  author={YanYang Li and Qiang Wang and Tong Xiao and T Liu and Jingbo Zhu},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.06546}
}

@article{Hassan2018AchievingHP,
  title={Achieving Human Parity on Automatic Chinese to English News Translation},
  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 Mengnan 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},
  journal={ArXiv},
  year={2018},
  volume={abs/1803.05567}
}

@article{StahlbergNeural,
  title={Neural Machine Translation: A Review},
  author={Stahlberg, Felix},
}

@inproceedings{Bentivogli2016NeuralVP,
  title={Neural versus Phrase-Based Machine Translation Quality: a Case Study},
  author={Luisa Bentivogli and Arianna Bisazza and Mauro Cettolo and Marcello Federico},
  booktitle={EMNLP},
  year={2016}
}

@article{Gu2017NonAutoregressiveNM,
  title={Non-Autoregressive Neural Machine Translation},
  author={Jiatao Gu and James Bradbury and Caiming Xiong and Victor O. K. Li and Richard Socher},
  journal={ArXiv},
  year={2017},
  volume={abs/1711.02281}
}

@inproceedings{li-etal-2019-word,
    title = "On the Word Alignment from Neural Machine Translation",
    author = "Li, Xintong  and
      Li, Guanlin  and
      Liu, Lemao  and
      Meng, Max  and
      Shi, Shuming",
    booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/P19-1124",
    doi = "10.18653/v1/P19-1124",
    pages = "1293--1303",
    abstract = "Prior researches suggest that neural machine translation (NMT) captures word alignment through its attention mechanism, however, this paper finds attention may almost fail to capture word alignment for some NMT models. This paper thereby proposes two methods to induce word alignment which are general and agnostic to specific NMT models. Experiments show that both methods induce much better word alignment than attention. This paper further visualizes the translation through the word alignment induced by NMT. In particular, it analyzes the effect of alignment errors on translation errors at word level and its quantitative analysis over many testing examples consistently demonstrate that alignment errors are likely to lead to translation errors measured by different metrics.",
}

@inproceedings{Sun2019PatientKD,
  title={Patient Knowledge Distillation for BERT Model Compression},
  author={Siqi Sun and Yu Cheng and Zhe Gan and Jingjing Liu},
  booktitle={EMNLP/IJCNLP},
  year={2019}
}

@article{Wu2019PayLA,
  title={Pay Less Attention with Lightweight and Dynamic Convolutions},
  author={Felix Wu and Angela Fan and Alexei Baevski and Yann Dauphin and Michael Auli},
  journal={ArXiv},
  year={2019},
  volume={abs/1901.10430}
}

@inproceedings{Zhang2017PriorKI,
  title={Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization},
  author={Jiacheng Zhang and Yang Liu and Huanbo Luan and Jingfang Xu and Maosong Sun},
  booktitle={ACL},
  year={2017}
}

@article{Shaw2018SelfAttentionWR,
  title={Self-Attention with Relative Position Representations},
  author={Peter Shaw and Jakob Uszkoreit and Ashish Vaswani},
  journal={ArXiv},
  year={2018},
  volume={abs/1803.02155}
}

@article{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},
  journal   = {CoRR},
  volume    = {abs/1904.03107},
  year      = {2019},
  url       = {http://arxiv.org/abs/1904.03107},
  archivePrefix = {arXiv},
  eprint    = {1904.03107},
  timestamp = {Wed, 24 Apr 2019 12:21:25 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1904-03107.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@incollection{NIPS2014_5346,
title = {Sequence to Sequence Learning with Neural Networks},
author = {Sutskever, Ilya and Vinyals, Oriol and Le, Quoc V},
booktitle = {Advances in Neural Information Processing Systems 27},
editor = {Z. Ghahramani and M. Welling and C. Cortes and N. D. Lawrence and K. Q. Weinberger},
pages = {3104--3112},
year = {2014},
publisher = {Curran Associates, Inc.},
url = {http://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf}
}

@inproceedings{Xiao2019SharingAW,
  title={Sharing Attention Weights for Fast Transformer},
  author={Tong Xiao and Yinqiao Li and Jingbo Zhu and Zheng-tao Yu and T Liu},
  booktitle={IJCAI},
  year={2019}
}

@article{DBLP:journals/corr/PaulusXS17,
  author    = {Romain Paulus and
               Caiming Xiong and
               Richard Socher},
  title     = {A Deep Reinforced Model for Abstractive Summarization},
  journal   = {CoRR},
  volume    = {abs/1705.04304},
  year      = {2017},
  url       = {http://arxiv.org/abs/1705.04304},
  archivePrefix = {arXiv},
  eprint    = {1705.04304},
  timestamp = {Mon, 13 Aug 2018 16:48:58 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/PaulusXS17.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/RushCW15,
  author    = {Alexander M. Rush and
               Sumit Chopra and
               Jason Weston},
  title     = {A Neural Attention Model for Abstractive Sentence Summarization},
  journal   = {CoRR},
  volume    = {abs/1509.00685},
  year      = {2015},
  url       = {http://arxiv.org/abs/1509.00685},
  archivePrefix = {arXiv},
  eprint    = {1509.00685},
  timestamp = {Mon, 13 Aug 2018 16:46:49 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/RushCW15.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{kalchbrenner-blunsom-2013-recurrent,
    title = "Recurrent Continuous Translation Models",
    author = "Kalchbrenner, Nal  and
      Blunsom, Phil",
    booktitle = "Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2013",
    address = "Seattle, Washington, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/D13-1176",
    pages = "1700--1709",
}

//Simple Recurrent Units for Highly Parallelizable Recurrence
@article{Lei2017TrainingRA,
  title={Training RNNs as Fast as CNNs},
  author={Tao Lei and Yu Zhang and Yoav Artzi},
  journal={ArXiv},
  year={2017},
  volume={abs/1709.02755}
}

@inproceedings{Zhang2018SimplifyingNM,
  title={Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks},
  author={Biao Zhang and Deyi Xiong and Jinsong Su and Qian Lin and Huiji Zhang},
  booktitle={EMNLP},
  year={2018}
}

@inproceedings{Zhang2018SpeedingUN,
  title={Speeding Up Neural Machine Translation Decoding by Cube Pruning},
  author={Wen Zhang and Liang Huang and Yang Feng and Lei Shen and Qun Liu},
  booktitle={EMNLP},
  year={2018}
}

@article{Chen2018TheBO,
  title={The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation},
  author={Mia Xu Chen and Orhan Firat and Ankur Bapna and Melvin Johnson and Wolfgang Macherey and George Foster and Llion Jones and Niki Parmar and Michael Schuster and Zhi-Feng Chen and Yonghui Wu and Macduff Hughes},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.09849}
}

@article{HochreiterThe,
  title={The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions},
  author={Hochreiter, S.},
  journal={International Journal of Uncertainty, Fuzziness and Knowledge-Based  Systems},
  volume={6},
  number={2},
  pages={107---116116},
}

@inproceedings{Yang2017TowardsBH,
  title={Towards Bidirectional Hierarchical Representations for Attention-based Neural Machine Translation},
  author={Baosong Yang and Derek F. Wong and Tong Xiao and Lidia S. Chao and Jingbo Zhu},
  booktitle={EMNLP},
  year={2017}
}

@inproceedings{Dai2019TransformerXLAL,
  title={Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context},
  author={Zihang Dai and Zhilin Yang and Yiming Yang and Jaime G. Carbonell and Quoc V. Le and Ruslan Salakhutdinov},
  booktitle={ACL},
  year={2019}
}

@article{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},
  journal   = {CoRR},
  volume    = {abs/1808.09374},
  year      = {2018},
  url       = {http://arxiv.org/abs/1808.09374},
  archivePrefix = {arXiv},
  eprint    = {1808.09374},
  timestamp = {Mon, 03 Sep 2018 13:36:40 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1808-09374.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-1809-01854,
  author    = {Jetic Gu and
               Hassan Shavarani and
               Anoop Sarkar},
  title     = {Top-down Tree Structured Decoding with Syntactic Connections for Neural
               Machine Translation and Parsing},
  journal   = {CoRR},
  volume    = {abs/1809.01854},
  year      = {2018},
  url       = {http://arxiv.org/abs/1809.01854},
  archivePrefix = {arXiv},
  eprint    = {1809.01854},
  timestamp = {Fri, 05 Oct 2018 11:34:52 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1809-01854.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{Wang2019TreeTI,
  title={Tree Transformer: Integrating Tree Structures into Self-Attention},
  author={Yau-Shian Wang and Hung-yi Lee and Yun-Nung Chen},
  booktitle={EMNLP/IJCNLP},
  year={2019}
}

@inproceedings{Werlen2018DocumentLevelNM,
  title={Document-Level Neural Machine Translation with Hierarchical Attention Networks},
  author={Lesly Miculicich Werlen and Dhananjay Ram and Nikolaos Pappas and James Henderson},
  booktitle={EMNLP},
  year={2018}
}

@inproceedings{Zhang2017Fast,
  title={Fast Parallel Training of Neural Language Models},
  author={Zhang, Chunliang and Tong, Xiao and Zhu, Jingbo and Liu, Tongran},
  year={2017},
}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%