Skip to content

T
Toy-MT-Introduction
Commit 9e88ca2f by 曹润柘
Options

合并分支 'caorunzhe' 到 'master' 

更换封皮和章节图片

查看合并请求 !21
parents 382fb044 30726017
正在显示 包含 676 行增加 和 23 行删除
Book/Chapter1/chapter1.tex
...@@ -8,7 +8,7 @@ ...@@ -8,7 +8,7 @@
%---------------------------------------------------------------------------------------- %----------------------------------------------------------------------------------------
\renewcommand\figurename{图}%将figure改为图 \renewcommand\figurename{图}%将figure改为图
\renewcommand\tablename{表}%将figure改为图 \renewcommand\tablename{表}%将figure改为图
\chapterimage{chapter_head_1.pdf} % Chapter heading image \chapterimage{fig-NEU-2.jpg} % Chapter heading image
\chapter{机器翻译简介} \chapter{机器翻译简介}
\section{机器翻译的概念}\index{Chapter1.1} \section{机器翻译的概念}\index{Chapter1.1}
......
Book/Chapter2/chapter2.tex
...@@ -8,7 +8,7 @@ ...@@ -8,7 +8,7 @@
\renewcommand\figurename{图}%将figure改为图 \renewcommand\figurename{图}%将figure改为图
\renewcommand\tablename{表}%将figure改为图 \renewcommand\tablename{表}%将figure改为图
%\renewcommand\arraystretch{1.5}%将表格高度调整为1.5倍 %\renewcommand\arraystretch{1.5}%将表格高度调整为1.5倍
\chapterimage{chapter_head_1.pdf} % Chapter heading image \chapterimage{fig-NEU-3.jpg} % Chapter heading image
\chapter{词法、语法及统计建模基础} \chapter{词法、语法及统计建模基础}
......
Book/Chapter3/Chapter3.tex
...@@ -8,7 +8,7 @@ ...@@ -8,7 +8,7 @@
\renewcommand\tablename{表}%将figure改为图 \renewcommand\tablename{表}%将figure改为图
\definecolor{ublue}{rgb}{0.152,0.250,0.545} \definecolor{ublue}{rgb}{0.152,0.250,0.545}
\definecolor{ugreen}{rgb}{0,0.5,0} \definecolor{ugreen}{rgb}{0,0.5,0}
\chapterimage{chapter_head_1} % Chapter heading image \chapterimage{fig-NEU-4.jpg} % Chapter heading image
%公式1.7之后往后串一个 %公式1.7之后往后串一个
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\chapter{基于词的机器翻译模型} \chapter{基于词的机器翻译模型}
......
Book/Chapter4/chapter4.tex
...@@ -6,7 +6,7 @@ ...@@ -6,7 +6,7 @@
%---------------------------------------------------------------------------------------- %----------------------------------------------------------------------------------------
\renewcommand\figurename{图}%将figure改为图 \renewcommand\figurename{图}%将figure改为图
\renewcommand\tablename{表}%将figure改为图 \renewcommand\tablename{表}%将figure改为图
\chapterimage{chapter_head_1.pdf} % Chapter heading image \chapterimage{fig-NEU-5.jpg} % Chapter heading image
\chapter{基于短语和句法的机器翻译模型} \chapter{基于短语和句法的机器翻译模型}
......
Book/Chapter5/chapter5.tex
...@@ -8,7 +8,7 @@ ...@@ -8,7 +8,7 @@
\renewcommand\figurename{图}%将figure改为图 \renewcommand\figurename{图}%将figure改为图
\renewcommand\tablename{表}%将figure改为图 \renewcommand\tablename{表}%将figure改为图
%\renewcommand\arraystretch{1.5}%将表格高度调整为1.5倍 %\renewcommand\arraystretch{1.5}%将表格高度调整为1.5倍
\chapterimage{chapter_head_1.pdf} % Chapter heading image \chapterimage{fig-NEU-6.jpg} % Chapter heading image
\chapter{人工神经网络和神经语言建模} \chapter{人工神经网络和神经语言建模}
......
Book/Chapter6/Chapter6.tex
...@@ -8,7 +8,7 @@ ...@@ -8,7 +8,7 @@
\renewcommand\tablename{表}%将figure改为图 \renewcommand\tablename{表}%将figure改为图
\definecolor{ublue}{rgb}{0.152,0.250,0.545} \definecolor{ublue}{rgb}{0.152,0.250,0.545}
\definecolor{ugreen}{rgb}{0,0.5,0} \definecolor{ugreen}{rgb}{0,0.5,0}
\chapterimage{chapter_head_1} % Chapter heading image \chapterimage{fig-NEU-7.jpg} % Chapter heading image
%------------------------------------------------ %------------------------------------------------
%公式1.7之后往后串一个 %公式1.7之后往后串一个
......
Book/ChapterAppend/ChapterAppend.tex
...@@ -8,7 +8,7 @@ ...@@ -8,7 +8,7 @@
%---------------------------------------------------------------------------------------- %----------------------------------------------------------------------------------------
\renewcommand\figurename{图}%将figure改为图 \renewcommand\figurename{图}%将figure改为图
\renewcommand\tablename{表}%将figure改为图 \renewcommand\tablename{表}%将figure改为图
\chapterimage{chapter_head_1} % Chapter heading image \chapterimage{fig-NEU-9.jpg} % Chapter heading image
%------------------------------------------------ %------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%第一章附录 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%第一章附录
......
Book/bibliography.bib
...@@ -4036,4 +4036,658 @@ pages ={157-166}, ...@@ -4036,4 +4036,658 @@ pages ={157-166},
%%%%% chapter 6---------------------------------------------------------------- %%%%% chapter 6----------------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 7------------------------------------------------------
@article{姚树杰2011基于句对质量和覆盖度的统计机器翻译训练语料选取,
title={基于句对质量和覆盖度的统计机器翻译训练语料选取},
author={姚树杰 and 肖桐 and 朱靖波},
journal={中文信息学报},
volume={25},
number={2},
pages={72-78},
year={2011},
}
%%%%%%%%%%%%%%%
@misc{provilkov2019bpedropout,
title={BPE-Dropout: Simple and Effective Subword Regularization},
author={Ivan Provilkov and Dmitrii Emelianenko and Elena Voita},
year={2019},
eprint={1910.13267},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
%%%%%%%%%%%%%%%%%%%
@article{DBLP:journals/corr/SennrichHB15,
author = {Rico Sennrich and
Barry Haddow and
Alexandra Birch},
title = {Neural Machine Translation of Rare Words with Subword Units},
journal = {CoRR},
volume = {abs/1508.07909},
year = {2015},
url = {http://arxiv.org/abs/1508.07909},
archivePrefix = {arXiv},
eprint = {1508.07909},
timestamp = {Mon, 13 Aug 2018 16:47:17 +0200},
biburl = {https://dblp.org/rec/journals/corr/SennrichHB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{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},
journal = {CoRR},
volume = {abs/1207.0580},
year = {2012},
url = {http://arxiv.org/abs/1207.0580},
archivePrefix = {arXiv},
eprint = {1207.0580},
timestamp = {Mon, 13 Aug 2018 16:46:10 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1207-0580.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{Hornic1989Multilayer,
title={Multilayer feedforward networks are universal approximators},
author={Hornic, K},
journal={Neural Networks},
volume={2},
number={5},
pages={359-366},
year={1989},
}
@article{DBLP:journals/corr/abs-1809-10853,
author = {Alexei Baevski and
Michael Auli},
title = {Adaptive Input Representations for Neural Language Modeling},
journal = {CoRR},
volume = {abs/1809.10853},
year = {2018},
url = {http://arxiv.org/abs/1809.10853},
archivePrefix = {arXiv},
eprint = {1809.10853},
timestamp = {Fri, 05 Oct 2018 11:34:52 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1809-10853.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{Stahlberg2019OnNS,
title={On NMT Search Errors and Model Errors: Cat Got Your Tongue?},
author={Felix Stahlberg and Bill Byrne},
booktitle={EMNLP/IJCNLP},
year={2019}
}
@article{DBLP:journals/corr/abs-1810-08398,
author = {Mingbo Ma and
Liang Huang and
Hao Xiong and
Kaibo Liu and
Chuanqiang Zhang and
Zhongjun He and
Hairong Liu and
Xing Li and
Haifeng Wang},
title = {{STACL:} Simultaneous Translation with Integrated Anticipation and
Controllable Latency},
journal = {CoRR},
volume = {abs/1810.08398},
year = {2018},
url = {http://arxiv.org/abs/1810.08398},
archivePrefix = {arXiv},
eprint = {1810.08398},
timestamp = {Thu, 01 Nov 2018 11:22:30 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1810-08398.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/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},
journal = {CoRR},
volume = {abs/1707.06885},
year = {2017},
url = {http://arxiv.org/abs/1707.06885},
archivePrefix = {arXiv},
eprint = {1707.06885},
timestamp = {Mon, 13 Aug 2018 16:48:37 +0200},
biburl = {https://dblp.org/rec/journals/corr/StahlbergHSB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SennrichHB16,
author = {Rico Sennrich and
Barry Haddow and
Alexandra Birch},
title = {Edinburgh Neural Machine Translation Systems for {WMT} 16},
journal = {CoRR},
volume = {abs/1606.02891},
year = {2016},
url = {http://arxiv.org/abs/1606.02891},
archivePrefix = {arXiv},
eprint = {1606.02891},
timestamp = {Mon, 13 Aug 2018 16:46:23 +0200},
biburl = {https://dblp.org/rec/journals/corr/SennrichHB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@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},
editor = {Ondrej Bojar and
Rajen Chatterjee and
Christian Federmann and
Mark Fishel and
Yvette Graham and
Barry Haddow and
Matthias Huck and
Antonio Jimeno{-}Yepes and
Philipp Koehn and
Andr{\'{e}} Martins and
Christof Monz and
Matteo Negri and
Aur{\'{e}}lie N{\'{e}}v{\'{e}}ol and
Mariana L. Neves and
Matt Post and
Marco Turchi and
Karin Verspoor},
title = {The NiuTrans Machine Translation Systems for {WMT19}},
booktitle = {Proceedings of the Fourth Conference on Machine Translation, {WMT}
2019, Florence, Italy, August 1-2, 2019 - Volume 2: Shared Task Papers,
Day 1},
pages = {257--266},
publisher = {Association for Computational Linguistics},
year = {2019},
url = {https://doi.org/10.18653/v1/w19-5325},
doi = {10.18653/v1/w19-5325},
timestamp = {Tue, 28 Jan 2020 10:30:56 +0100},
biburl = {https://dblp.org/rec/conf/wmt/LiLXLLLWZXWFCLL19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/DabreF19,
author = {Raj Dabre and
Atsushi Fujita},
title = {Recurrent Stacking of Layers for Compact Neural Machine Translation
Models},
booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI}
2019, The Thirty-First Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii,
USA, January 27 - February 1, 2019},
pages = {6292--6299},
publisher = {{AAAI} Press},
year = {2019},
url = {https://doi.org/10.1609/aaai.v33i01.33016292},
doi = {10.1609/aaai.v33i01.33016292},
timestamp = {Wed, 25 Sep 2019 11:05:09 +0200},
biburl = {https://dblp.org/rec/conf/aaai/DabreF19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1712-05877,
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},
journal = {CoRR},
volume = {abs/1712.05877},
year = {2017},
url = {http://arxiv.org/abs/1712.05877},
archivePrefix = {arXiv},
eprint = {1712.05877},
timestamp = {Mon, 13 Aug 2018 16:48:27 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1712-05877.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-10485,
author = {Gabriele Prato and
Ella Charlaix and
Mehdi Rezagholizadeh},
title = {Fully Quantized Transformer for Improved Translation},
journal = {CoRR},
volume = {abs/1910.10485},
year = {2019},
url = {http://arxiv.org/abs/1910.10485},
archivePrefix = {arXiv},
eprint = {1910.10485},
timestamp = {Fri, 25 Oct 2019 14:59:26 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-10485.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1801-05122,
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},
journal = {CoRR},
volume = {abs/1801.05122},
year = {2018},
url = {http://arxiv.org/abs/1801.05122},
archivePrefix = {arXiv},
eprint = {1801.05122},
timestamp = {Mon, 15 Jul 2019 14:17:41 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1801-05122.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1809-00069,
author = {Liang Huang and
Kai Zhao and
Mingbo Ma},
title = {When to Finish? Optimal Beam Search for Neural Text Generation (modulo
beam size)},
journal = {CoRR},
volume = {abs/1809.00069},
year = {2018},
url = {http://arxiv.org/abs/1809.00069},
archivePrefix = {arXiv},
eprint = {1809.00069},
timestamp = {Fri, 05 Oct 2018 11:34:52 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1809-00069.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{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},
journal = {J. Comput. Syst. Sci.},
volume = {55},
number = {1},
pages = {119--139},
year = {1997},
url = {https://doi.org/10.1006/jcss.1997.1504},
doi = {10.1006/jcss.1997.1504},
timestamp = {Wed, 14 Nov 2018 10:33:59 +0100},
biburl = {https://dblp.org/rec/journals/jcss/FreundS97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/XiaoZZW10,
author = {Tong Xiao and
Jingbo Zhu and
Muhua Zhu and
Huizhen Wang},
editor = {Jan Hajic and
Sandra Carberry and
Stephen Clark},
title = {Boosting-Based System Combination for Machine Translation},
booktitle = {{ACL} 2010, Proceedings of the 48th Annual Meeting of the Association
for Computational Linguistics, July 11-16, 2010, Uppsala, Sweden},
pages = {739--748},
publisher = {The Association for Computer Linguistics},
year = {2010},
url = {https://www.aclweb.org/anthology/P10-1076/},
timestamp = {Fri, 13 Sep 2019 13:00:43 +0200},
biburl = {https://dblp.org/rec/conf/acl/XiaoZZW10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@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},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April
15-20, 2007},
pages = {105--108},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ICASSP.2007.367174},
doi = {10.1109/ICASSP.2007.367174},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SimBGSW07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/RostiMS07,
author = {Antti{-}Veikko I. Rosti and
Spyridon Matsoukas and
Richard M. Schwartz},
editor = {John A. Carroll and
Antal van den Bosch and
Annie Zaenen},
title = {Improved Word-Level System Combination for Machine Translation},
booktitle = {{ACL} 2007, Proceedings of the 45th Annual Meeting of the Association
for Computational Linguistics, June 23-30, 2007, Prague, Czech Republic},
publisher = {The Association for Computational Linguistics},
year = {2007},
url = {https://www.aclweb.org/anthology/P07-1040/},
timestamp = {Mon, 16 Sep 2019 13:46:41 +0200},
biburl = {https://dblp.org/rec/conf/acl/RostiMS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wmt/RostiZMS08,
author = {Antti{-}Veikko I. Rosti and
Bing Zhang and
Spyros Matsoukas and
Richard M. Schwartz},
editor = {Chris Callison{-}Burch and
Philipp Koehn and
Christof Monz and
Josh Schroeder and
Cameron S. Fordyce},
title = {Incremental Hypothesis Alignment for Building Confusion Networks with
Application to Machine Translation System Combination},
booktitle = {Proceedings of the Third Workshop on Statistical Machine Translation,
WMT@ACL 2008, Columbus, Ohio, USA, June 19, 2008},
pages = {183--186},
publisher = {Association for Computational Linguistics},
year = {2008},
url = {https://www.aclweb.org/anthology/W08-0329/},
timestamp = {Fri, 13 Sep 2019 13:08:46 +0200},
biburl = {https://dblp.org/rec/conf/wmt/RostiZMS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LiMJ16,
author = {Jiwei Li and
Will Monroe and
Dan Jurafsky},
title = {A Simple, Fast Diverse Decoding Algorithm for Neural Generation},
journal = {CoRR},
volume = {abs/1611.08562},
year = {2016},
url = {http://arxiv.org/abs/1611.08562},
archivePrefix = {arXiv},
eprint = {1611.08562},
timestamp = {Mon, 13 Aug 2018 16:48:46 +0200},
biburl = {https://dblp.org/rec/journals/corr/LiMJ16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@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},
booktitle = {2008 Conference on Empirical Methods in Natural Language Processing,
{EMNLP} 2008, Proceedings of the Conference, 25-27 October 2008, Honolulu,
Hawaii, USA, {A} meeting of SIGDAT, a Special Interest Group of the
{ACL}},
pages = {620--629},
publisher = {{ACL}},
year = {2008},
url = {https://www.aclweb.org/anthology/D08-1065/},
timestamp = {Fri, 13 Sep 2019 13:08:45 +0200},
biburl = {https://dblp.org/rec/conf/emnlp/TrombleKOM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/SuTXJSL17,
author = {Jinsong Su and
Zhixing Tan and
Deyi Xiong and
Rongrong Ji and
Xiaodong Shi and
Yang Liu},
editor = {Satinder P. Singh and
Shaul Markovitch},
title = {Lattice-Based Recurrent Neural Network Encoders for Neural Machine
Translation},
booktitle = {Proceedings of the Thirty-First {AAAI} Conference on Artificial Intelligence,
February 4-9, 2017, San Francisco, California, {USA}},
pages = {3302--3308},
publisher = {{AAAI} Press},
year = {2017},
url = {http://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14320},
timestamp = {Sun, 31 Mar 2019 12:09:37 +0200},
biburl = {https://dblp.org/rec/conf/aaai/SuTXJSL17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/BirdL04,
author = {Steven Bird and
Edward Loper},
title = {{NLTK:} The Natural Language Toolkit},
booktitle = {Proceedings of the 42nd Annual Meeting of the Association for Computational
Linguistics, Barcelona, Spain, July 21-26, 2004 - Poster and Demonstration},
publisher = {{ACL}},
year = {2004},
url = {https://www.aclweb.org/anthology/P04-3031/},
timestamp = {Wed, 18 Sep 2019 12:15:54 +0200},
biburl = {https://dblp.org/rec/conf/acl/BirdL04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{wang-etal-2018-dynamic,
title = "Dynamic Sentence Sampling for Efficient Training of Neural Machine Translation",
author = "Wang, Rui and
Utiyama, Masao and
Sumita, Eiichiro",
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/P18-2048",
doi = "10.18653/v1/P18-2048",
pages = "298--304",
abstract = "Traditional Neural machine translation (NMT) involves a fixed training procedure where each sentence is sampled once during each epoch. In reality, some sentences are well-learned during the initial few epochs; however, using this approach, the well-learned sentences would continue to be trained along with those sentences that were not well learned for 10-30 epochs, which results in a wastage of time. Here, we propose an efficient method to dynamically sample the sentences in order to accelerate the NMT training. In this approach, a weight is assigned to each sentence based on the measured difference between the training costs of two iterations. Further, in each epoch, a certain percentage of sentences are dynamically sampled according to their weights. Empirical results based on the NIST Chinese-to-English and the WMT English-to-German tasks show that the proposed method can significantly accelerate the NMT training and improve the NMT performance.",
}
@inproceedings{garciamartinez:hal-01433161,
TITLE = {{Factored Neural Machine Translation Architectures}},
AUTHOR = {Garcia-Martinez, Mercedes and Barrault, Lo{\"i}c and Bougares, Fethi},
URL = {https://hal.archives-ouvertes.fr/hal-01433161},
BOOKTITLE = {{International Workshop on Spoken Language Translation (IWSLT'16)}},
ADDRESS = {Seattle, United States},
YEAR = {2016},
PDF = {https://hal.archives-ouvertes.fr/hal-01433161/file/FNMTiwslt2016.pdf},
HAL_ID = {hal-01433161},
HAL_VERSION = {v1},
}
@article{DBLP:journals/corr/JeanCMB14,
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},
journal = {CoRR},
volume = {abs/1412.2007},
year = {2014},
url = {http://arxiv.org/abs/1412.2007},
archivePrefix = {arXiv},
eprint = {1412.2007},
timestamp = {Mon, 13 Aug 2018 16:46:10 +0200},
biburl = {https://dblp.org/rec/journals/corr/JeanCMB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LuongM16,
author = {Minh{-}Thang Luong and
Christopher D. Manning},
title = {Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character
Models},
journal = {CoRR},
volume = {abs/1604.00788},
year = {2016},
url = {http://arxiv.org/abs/1604.00788},
archivePrefix = {arXiv},
eprint = {1604.00788},
timestamp = {Mon, 13 Aug 2018 16:47:26 +0200},
biburl = {https://dblp.org/rec/journals/corr/LuongM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{philipAlgorithmfordataCompression,
title={A New Algorithm for Data Compression},
author={Philip Gage},
year = {1994}
}
@article{DBLP:journals/corr/abs-1804-10959,
author = {Taku Kudo},
title = {Subword Regularization: Improving Neural Network Translation Models
with Multiple Subword Candidates},
journal = {CoRR},
volume = {abs/1804.10959},
year = {2018},
url = {http://arxiv.org/abs/1804.10959},
archivePrefix = {arXiv},
eprint = {1804.10959},
timestamp = {Mon, 13 Aug 2018 16:48:57 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-10959.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZagoruykoK16,
author = {Sergey Zagoruyko and
Nikos Komodakis},
title = {Wide Residual Networks},
journal = {CoRR},
volume = {abs/1605.07146},
year = {2016},
url = {http://arxiv.org/abs/1605.07146},
archivePrefix = {arXiv},
eprint = {1605.07146},
timestamp = {Mon, 13 Aug 2018 16:46:42 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZagoruykoK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/iet-bmt/Sepas-Moghaddam20,
author = {Alireza Sepas{-}Moghaddam and
Fernando Pereira and
Paulo Lobato Correia},
title = {Face recognition: a novel multi-level taxonomy based survey},
journal = {{IET} Biom.},
volume = {9},
number = {2},
pages = {58--67},
year = {2020},
url = {https://doi.org/10.1049/iet-bmt.2019.0001},
doi = {10.1049/iet-bmt.2019.0001},
timestamp = {Wed, 01 Apr 2020 08:42:20 +0200},
biburl = {https://dblp.org/rec/journals/iet-bmt/Sepas-Moghaddam20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{ethayarajh-2019-contextual,
title = "How Contextual are Contextualized Word Representations? Comparing the Geometry of {BERT}, {ELM}o, and {GPT}-2 Embeddings",
author = "Ethayarajh, Kawin",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/D19-1006",
doi = "10.18653/v1/D19-1006",
pages = "55--65",
abstract = "Replacing static word embeddings with contextualized word representations has yielded significant improvements on many NLP tasks. However, just how contextual are the contextualized representations produced by models such as ELMo and BERT? Are there infinitely many context-specific representations for each word, or are words essentially assigned one of a finite number of word-sense representations? For one, we find that the contextualized representations of all words are not isotropic in any layer of the contextualizing model. While representations of the same word in different contexts still have a greater cosine similarity than those of two different words, this self-similarity is much lower in upper layers. This suggests that upper layers of contextualizing models produce more context-specific representations, much like how upper layers of LSTMs produce more task-specific representations. In all layers of ELMo, BERT, and GPT-2, on average, less than 5{\%} of the variance in a word{'}s contextualized representations can be explained by a static embedding for that word, providing some justification for the success of contextualized representations.",
}
@inproceedings{DBLP:conf/acl/JawaharSS19,
author = {Ganesh Jawahar and
Beno{\^{\i}}t Sagot and
Djam{\'{e}} Seddah},
editor = {Anna Korhonen and
David R. Traum and
Llu{\'{\i}}s M{\`{a}}rquez},
title = {What Does {BERT} Learn about the Structure of Language?},
booktitle = {Proceedings of the 57th Conference of the Association for Computational
Linguistics, {ACL} 2019, Florence, Italy, July 28- August 2, 2019,
Volume 1: Long Papers},
pages = {3651--3657},
publisher = {Association for Computational Linguistics},
year = {2019},
url = {https://doi.org/10.18653/v1/p19-1356},
doi = {10.18653/v1/p19-1356},
timestamp = {Tue, 28 Jan 2020 10:28:06 +0100},
biburl = {https://dblp.org/rec/conf/acl/JawaharSS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-00187,
author = {Myle Ott and
Sergey Edunov and
David Grangier and
Michael Auli},
title = {Scaling Neural Machine Translation},
journal = {CoRR},
volume = {abs/1806.00187},
year = {2018},
url = {http://arxiv.org/abs/1806.00187},
archivePrefix = {arXiv},
eprint = {1806.00187},
timestamp = {Mon, 13 Aug 2018 16:47:40 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-00187.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{bengioCurriculumlearning,
author = {Yoshu Bengio and
Jerome Louradour and
Ronman Collobert and
Jason Weston},
title = {Curriculum learning}
}
@inproceedings{Hubara2016BinarizedNN,
title={Binarized Neural Networks},
author={Itay Hubara and Matthieu Courbariaux and Daniel Soudry and Ran El-Yaniv and Yoshua Bengio},
booktitle={NIPS},
year={2016}
}
@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},
booktitle = {Proceedings of the 2009 Conference on Empirical Methods in Natural
Language Processing, {EMNLP} 2009, 6-7 August 2009, Singapore, {A}
meeting of SIGDAT, a Special Interest Group of the {ACL}},
pages = {1096--1104},
publisher = {{ACL}},
year = {2009},
url = {https://www.aclweb.org/anthology/D09-1114/},
timestamp = {Fri, 13 Sep 2019 13:08:45 +0200},
biburl = {https://dblp.org/rec/conf/emnlp/DuanLXZ09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
Book/mt-book-xelatex.tex
...@@ -53,12 +53,10 @@ ...@@ -53,12 +53,10 @@
\begingroup \begingroup
\thispagestyle{empty} % Suppress headers and footers on the title page \thispagestyle{empty} % Suppress headers and footers on the title page
%\begin{tikzpicture}[remember picture,overlay]
\begin{tikzpicture}[remember picture,overlay] \begin{tikzpicture}[remember picture,overlay]
\node[inner sep=0pt] (background) at (current page.center) {\includegraphics[width=\paperwidth]{background.pdf}}; \node[inner sep=0pt] (background) at (current page.center) {\includegraphics[width=\paperwidth,height=\paperheight]{fig-cover.jpg}};
\draw (current page.center) node [fill=ocre!30!white,fill opacity=0.6,text opacity=1,inner sep=1cm]{\Huge\centering\bfseries\sffamily\parbox[c][][t]{\paperwidth}{\centering 机器翻译：统计建模与深度学习方法\\[15pt] % Book title
%{\Large 副标题是否需要}\\[20pt] % Subtitle
{\LARGE 肖桐\ \ 朱靖波}}}; % Author name
\end{tikzpicture} \end{tikzpicture}
\vfill \vfill
\endgroup \endgroup
...@@ -95,11 +93,12 @@ ...@@ -95,11 +93,12 @@
\noindent 曹润柘、曾信、孟霞、单韦乔、姜雨帆、王子扬、刘辉、许诺、李北、刘继强、张哲旸、周书涵、周涛、张裕浩、李炎洋、林野、刘晓倩、牛蕊 \\ \noindent 曹润柘、曾信、孟霞、单韦乔、姜雨帆、王子扬、刘辉、许诺、李北、刘继强、张哲旸、周书涵、周涛、张裕浩、李炎洋、林野、刘晓倩、牛蕊 \\
} }
%---------------------------------------------------------------------------------------- %----------------------------------------------------------------------------------------
% TABLE OF CONTENTS % TABLE OF CONTENTS
%---------------------------------------------------------------------------------------- %----------------------------------------------------------------------------------------
%\usechapterimagefalse % If you don't want to include a chapter image, use this to toggle images off - it can be enabled later with \usechapterimagetrue %\usechapterimagefalse % If you don't want to include a chapter image, use this to toggle images off - it can be enabled later with \usechapterimagetrue
\chapterimage{chapter_head_1.pdf} %目录标题的图案 \chapterimage{fig-NEU-1.jpg} %目录标题的图案
\pagestyle{empty} % Disable headers and footers for the following pages \pagestyle{empty} % Disable headers and footers for the following pages
\tableofcontents % 打印目录 \tableofcontents % 打印目录
\cleardoublepage %保证章节页在奇数页 \cleardoublepage %保证章节页在奇数页
...@@ -111,19 +110,21 @@ ...@@ -111,19 +110,21 @@
% CHAPTERS % CHAPTERS
%---------------------------------------------------------------------------------------- %----------------------------------------------------------------------------------------
%\include{Chapter1/chapter1} \include{Chapter1/chapter1}
%\include{Chapter2/chapter2} \include{Chapter2/chapter2}
%\include{Chapter3/chapter3} \include{Chapter3/chapter3}
\include{Chapter4/chapter4} \include{Chapter4/chapter4}
%\include{Chapter5/chapter5} \include{Chapter5/chapter5}
%\include{Chapter6/chapter6} \include{Chapter6/chapter6}
%\include{ChapterAppend/chapterappend} %\include{Chapter7/chapter7}
\include{ChapterAppend/chapterappend}
%---------------------------------------------------------------------------------------- %----------------------------------------------------------------------------------------
% BIBLIOGRAPHY % BIBLIOGRAPHY
%---------------------------------------------------------------------------------------- %----------------------------------------------------------------------------------------
\chapterimage{fig-NEU-10.jpg} %目录标题的图案
\cleardoublepage % Make sure the index starts on an odd (right side) page \cleardoublepage % Make sure the index starts on an odd (right side) page
\printbibliography \printbibliography
...@@ -132,7 +133,7 @@ ...@@ -132,7 +133,7 @@
%---------------------------------------------------------------------------------------- %----------------------------------------------------------------------------------------
% INDEX % INDEX
%---------------------------------------------------------------------------------------- %----------------------------------------------------------------------------------------
\chapterimage{fig-NEU-10.jpg} %目录标题的图案
\cleardoublepage % Make sure the index starts on an odd (right side) page \cleardoublepage % Make sure the index starts on an odd (right side) page
%\phantomsection %\phantomsection
%\setlength{\columnsep}{0.75cm} % Space between the 2 columns of the index %\setlength{\columnsep}{0.75cm} % Space between the 2 columns of the index
......
Book/structure.tex
...@@ -547,7 +547,7 @@ addtohook={% ...@@ -547,7 +547,7 @@ addtohook={%
\usetikzlibrary{mindmap,backgrounds} % mind map \usetikzlibrary{mindmap,backgrounds} % mind map
\usepackage{type1cm}%设置公式字体 \usepackage{type1cm}%设置公式字体
\usepackage{caption}%设置图片标题字体大小 \usepackage{caption}%设置图片标题字体大小
\captionsetup{font={small}} \captionsetup{font={footnotesize}}
\usepackage{pstricks} \usepackage{pstricks}
\DeclareMathOperator*{\argmax}{arg\,max} \DeclareMathOperator*{\argmax}{arg\,max}
\DeclareMathOperator*{\argmin}{arg\,min} \DeclareMathOperator*{\argmin}{arg\,min}
...@@ -620,5 +620,3 @@ addtohook={% ...@@ -620,5 +620,3 @@ addtohook={%
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论