Skip to content

M
mtbookv2
Commit dd847e99 by 曹润柘
Options

update chapter 5

parent a7c0bb04
正在显示 包含 288 行增加 和 123 行删除
Chapter5/chapter5.tex
......@@ -1088,18 +1088,21 @@ c_{\mathbb{E}}(s_u|t_v)=\sum\limits_{i=1}^{N} c_{\mathbb{E}}(s_u|t_v;s^{[i]},t^
\sectionnewpage
\section{小结及深入阅读}
\parinterval 本章对IBM系列模型中的IBM模型1进行了详细的介绍和讨论，从一个简单的基于单词的翻译模型开始，本章从建模、解码、训练多个维度对统计机器翻译进行了描述，期间涉及了词对齐、优化等多个重要概念。IBM模型共分为5个模型，对翻译问题的建模依次由浅入深，同时模型复杂度也依次增加，我们将在下一章对IBM模型2-5进行详细的介绍和讨论。IBM模型作为入门统计机器翻译的``必经之路''，其思想对今天的机器翻译仍然产生着影响。虽然单独使用IBM模型进行机器翻译现在已经不多见，甚至很多从事神经机器翻译等前沿研究的人对IBM模型已经逐渐淡忘，但是不能否认IBM模型标志着一个时代的开始。从某种意义上讲，当使用公式$\hat{\vectorn{t}} = \argmax_{\vectorn{t}} \funp{P}(\vectorn{t}|\vectorn{s})$描述机器翻译问题的时候，或多或少都在与IBM模型使用相似的思想。
\parinterval 本章对IBM系列模型中的IBM模型1进行了详细的介绍和讨论，从一个简单的基于单词的翻译模型开始，本章从建模、解码、训练多个维度对统计机器翻译进行了描述，期间涉及了词对齐、优化等多个重要概念。IBM模型共分为5个模型，对翻译问题的建模依次由浅入深，同时模型复杂度也依次增加，我们将在{\chaptersix}对IBM模型2-5进行详细的介绍和讨论。IBM模型作为入门统计机器翻译的``必经之路''，其思想对今天的机器翻译仍然产生着影响。虽然单独使用IBM模型进行机器翻译现在已经不多见，甚至很多从事神经机器翻译等前沿研究的人对IBM模型已经逐渐淡忘，但是不能否认IBM模型标志着一个时代的开始。从某种意义上讲，当使用公式$\hat{\vectorn{t}} = \argmax_{\vectorn{t}} \funp{P}(\vectorn{t}|\vectorn{s})$描述机器翻译问题的时候，或多或少都在与IBM模型使用相似的思想。
{\color{red}词对齐需要扩充，还不太清楚具体是什么，需要问老师}
\parinterval 当然，本书也无法涵盖IBM模型的所有内涵，很多内容需要感兴趣的读者继续研究和挖掘，有两个方向可以考虑：
\parinterval 当然，本书也无法涵盖IBM模型的所有内涵，很多内容需要感兴趣的读者继续研究和挖掘。其中最值得关注的是统计词对齐问题。由于词对齐是IBM模型训练的间接产物，因此IBM模型成为了自动词对齐的重要方法。比如IBM模型训练装置GIZA++更多的是被用于自动词对齐任务，而非简单的训练IBM模型参数\upcite{och2003systematic}。
\begin{itemize}
\vspace{0.5em}
\item IBM模型在提出后的十余年中，一直受到了学术界的关注。一个比较有代表性的成果是GIZA++（\url{https://github.com/moses-smt/giza-pp}），它集成了IBM模型和隐马尔可夫模型，并实现了这些模型的训练。在随后相当长的一段时间里，GIZA++也是机器翻译研究的标配，用于获得双语平行数据上单词一级的对齐结果。此外，研究者也对IBM模型进行了大量的分析，为后人研究统计机器翻译提供了大量依据\cite{och2004alignment}。虽然IBM模型很少被独立使用，甚至直接用基于IBM模型的解码器也不多见，但是它通常会作为其他模型的一部分参与到对翻译的建模中。这部分工作会在下一章{\color{red}基于短语和句法的模型}中进行讨论\cite{koehn2003statistical}。此外，IBM模型也给机器翻译提供了一种非常简便的计算双语词串对应好坏的方式，因此也被广泛用于度量双语词串对应的强度，是自然语言处理中的一种常用特征。
\item 在IBM基础模型之上，有很多改进的工作。例如，对空对齐、低频词进行额外处理\upcite{DBLP:conf/acl/Moore04}；考虑源语言-目标语言和目标语言-源语言双向词对齐进行更好地词对齐对称化\upcite{肖桐1991面向统计机器翻译的重对齐方法研究}；使用词典、命名实体等多种信息对模型进行改进\upcite{2005Improving}；通过引入短语增强IBM基础模型\upcite{1998Grammar}；引入相邻单词对齐之间的依赖关系增加模型鲁棒性\upcite{DBLP:conf/acl-vlc/DaganCG93}等；也可以对IBM模型的正向和反向结果进行对称化处理，以得到更加准确词对齐结果\upcite{och2003systematic}。
\item 随着词对齐概念的不断深入，也有很多词对齐方面的工作并不依赖IBM模型。比如，可以直接使用判别式模型利用分类器解决词对齐问题\upcite{ittycheriah2005maximum}；使用带参数控制的动态规划方法来提高词对齐准确率\upcite{DBLP:conf/naacl/GaleC91}；甚至可以把对齐的思想用于短语和句法结构的双语对应\upcite{xiao2013unsupervised}；无监督的对称词对齐方法，正向和反向模型联合训练，结合数据的相似性\upcite{DBLP:conf/naacl/LiangTK06}；除了GIZA++，研究人员也开发了很多优秀的自动对齐工具，比如，FastAlign\upcite{DBLP:conf/naacl/DyerCS13}、Berkeley Aligner（\url{https://github.com/mhajiloo/berkeleyaligner}）等，这些工具现在也有很广发的应用。
\vspace{0.5em}
\item 除了在机器翻译建模上的开创性工作，IBM模型的另一项重要贡献是建立了统计词对齐的基础模型。在训练IBM模型的过程中，除了学习到模型参数，还可以得到双语数据上的词对齐结果。也就是说词对齐标注是IBM模型训练的间接产物。这也使得IBM模型成为了自动词对齐的重要方法。包括GIZA++在内的很多工作，实际上更多的是被用于自动词对齐任务，而非简单的训练IBM模型参数。随着词对齐概念的不断深入，这个任务逐渐成为了自然语言处理中的重要分支，比如，对IBM模型的结果进行对称化\cite{och2003systematic}，也可以直接使用判别式模型利用分类模型解决词对齐问题\cite{ittycheriah2005maximum}，甚至可以把对齐的思想用于短语和句法结构的双语对应\cite{xiao2013unsupervised}。除了GIZA++，研究人员也开发了很多优秀的自动词对齐工具，比如，FastAlign （\url{https://github.com/clab/fast_align}）、Berkeley Aligner（\url{https://github.com/mhajiloo/berkeleyaligner}）等，这些工具现在也有很广泛的应用。
\item 一种较为通用的词对齐评价标准是{\bfnew{对齐错误率}}(Alignment Error Rate, AER)\upcite{DBLP:journals/coling/FraserM07}。在此基础之上也可以对词对齐评价方法进行改进，以提高对齐质量与机器翻译评价得分BLEU的相关性\upcite{DBLP:conf/acl/DeNeroK07,paul2007all,黄书剑2009一种错误敏感的词对齐评价方法}。也有工作通过统计机器翻译系统性能的提升来评价对齐质量\upcite{DBLP:journals/coling/FraserM07}。不过，在相当长的时间内，词对齐质量对机器翻译系统的影响究竟如何并没有统一的结论。有些时候，词对齐的错误率下降了，但是机器翻译系统的译文品质没有带来性能提升。但是，这个问题比较复杂，需要进一步的论证。不过，可以肯定的是，词对齐可以帮助人们分析机器翻译的行为。甚至在最新的神经机器翻译中，如何在神经网络模型中寻求两种语言单词之间的对应关系也是对模型进行解释的有效手段之一\upcite{DBLP:journals/corr/FengLLZ16}。
\vspace{0.5em}
\item 基于单词的翻译模型的解码问题也是早期研究者所关注的。比较经典的方法的是贪婪方法\upcite{germann2003greedy}。也有研究者对不同的解码方法进行了对比\upcite{germann2001fast}，并给出了一些加速解码的思路。随后，也有工作进一步对这些方法进行改进\upcite{DBLP:conf/coling/UdupaFM04,DBLP:conf/naacl/RiedelC09}。实际上，基于单词的模型的解码是一个NP完全问题\upcite{knight1999decoding}，这也是为什么机器翻译的解码十分困难的原因。关于翻译模型解码算法的时间复杂度也有很多讨论\upcite{DBLP:conf/eacl/UdupaM06,DBLP:conf/emnlp/LeuschMN08,DBLP:journals/mt/FlemingKN15}。
\end{itemize}
......
bibliography.bib
......@@ -1053,46 +1053,50 @@
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},
publisher = {{ACL}},
year = {2002}
}
@article{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}
author = {Kenneth Ward Church and
Eduard H. Hovy},
title = {Good applications for crummy machine translation},
volume = {8},
number = {4},
pages = {239--258},
year = {1993}
}
@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},
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}
author = {Christoph Tillmann and
Stephan Vogel and
Hermann Ney and
A. Zubiaga and
Hassan Sawaf},
title = {Accelerated {DP} based search for statistical translation},
publisher = {{ISCA}},
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}
year={2006},
organization={Cambridge, MA}
}
@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},
publisher = {{ACL}},
year = {1992}
}
@inproceedings{DBLP:conf/emnlp/ChiangDCN08,
......@@ -1103,7 +1107,7 @@
title = {Decomposability of Translation Metrics for Improved Evaluation and
Efficient Algorithms},
pages = {610--619},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {{ACL}},
year = {2008}
}
@inproceedings{DBLP:conf/acl/BanerjeeL05,
......@@ -1112,7 +1116,7 @@
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},
publisher = {Association for Computational Linguistics},
year = {2005}
}
@inproceedings{DBLP:conf/wmt/DenkowskiL10,
......@@ -1121,7 +1125,7 @@
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},
publisher = {Association for Computational Linguistics},
year = {2010}
}
@inproceedings{DBLP:conf/wmt/DenkowskiL11,
......@@ -1130,7 +1134,7 @@
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},
publisher = {Association for Computational Linguistics},
year = {2011},
}
@inproceedings{DBLP:conf/wmt/DenkowskiL14,
......@@ -1139,7 +1143,7 @@
title = {Meteor Universal: Language Specific Translation Evaluation for Any
Target Language},
pages = {376--380},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {The Association for Computer Linguistics},
year = {2014}
}
@article{DBLP:journals/mt/Shiwen93,
......@@ -1160,7 +1164,6 @@
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}
}
......@@ -1169,14 +1172,14 @@
Rebecca Hwa},
title = {A Re-examination of Machine Learning Approaches for Sentence-Level
{MT} Evaluation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {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},
publisher = {The Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/naacl/LiuG07,
......@@ -1185,7 +1188,7 @@
title = {Source-Language Features and Maximum Correlation Training for Machine
Translation Evaluation},
pages = {41--48},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {The Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/ijcnlp/GimenezM08,
......@@ -1194,7 +1197,7 @@
title = {Heterogeneous Automatic {MT} Evaluation Through Non-Parametric Metric
Combinations},
pages = {319--326},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {The Association for Computer Linguistics},
year = {2008}
}
@inproceedings{DBLP:conf/naacl/DreyerM12,
......@@ -1202,7 +1205,7 @@
Daniel Marcu},
title = {HyTER: Meaning-Equivalent Semantics for Translation Evaluation},
pages = {162--171},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {The Association for Computational Linguistics},
year = {2012}
}
@inproceedings{DBLP:conf/tsd/BojarMTZ13,
......@@ -1211,6 +1214,7 @@
Ales Tamchyna and
Daniel Zeman},
title = {Scratching the Surface of Possible Translations},
series = {Lecture Notes in Computer Science},
volume = {8082},
pages = {465--474},
publisher = {Springer},
......@@ -1231,7 +1235,7 @@
Christopher D. Manning},
title = {Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions},
pages = {151--161},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {{ACL}},
year = {2011}
}
@inproceedings{DBLP:conf/emnlp/SocherPWCMNP13,
......@@ -1245,7 +1249,7 @@
title = {Recursive Deep Models for Semantic Compositionality Over a Sentiment
Treebank},
pages = {1631--1642},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {{ACL}},
year = {2013},
}
@article{DBLP:journals/corr/MatsuoKS17,
......@@ -1259,18 +1263,19 @@
year = {2017}
}
@article{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},
journal={Computer Speech \& Language},
volume={45},
pages={180--200},
year={2017},
publisher={Elsevier}
author = {Francisco Guzm{\'{a}}n and
Shafiq R. Joty and
Llu{\'{\i}}s M{\`{a}}rquez and
Preslav Nakov},
title = {Machine translation evaluation with neural networks},
journal = {Comput. Speech Lang.},
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}
}
......@@ -1306,12 +1311,12 @@
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}
author = {Pablo Fetter and
Fr{\'{e}}d{\'{e}}ric Dandurand and
Peter Regel-Brietzmann},
title = {Word graph rescoring using confidence measures},
publisher = {{ISCA}},
year = {1996}
}
@inproceedings{DBLP:conf/acl/ShenCHHWSL16,
author = {Shiqi Shen and
......@@ -1322,7 +1327,7 @@
Maosong Sun and
Yang Liu},
title = {Minimum Risk Training for Neural Machine Translation},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {The Association for Computer Linguistics},
year = {2016},
}
@inproceedings{DBLP:conf/wmt/FreitagCR19,
......@@ -1331,25 +1336,26 @@
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},
publisher = {Association for Computational Linguistics},
year = {2019}
}
@article{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},
journal={Machine Translation},
volume={27},
number={3-4},
pages={171--192},
year={2013},
publisher={Springer}
author = {Ergun Bi{\c{c}}ici and
Declan Groves and
Josef van Genabith},
title = {Predicting sentence translation quality using extrinsic and language
independent features},
journal = {Mach. Transl.},
volume = {27},
number = {3-4},
pages = {171--192}
}
@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},
publisher = {The Association for Computer Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/wmt/BiciciLW15a,
......@@ -1359,7 +1365,7 @@
title = {Referential Translation Machines for Predicting Translation Quality
and Related Statistics},
pages = {304--308},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {The Association for Computer Linguistics},
year = {2015}
}
@inproceedings{DBLP:conf/iclr/LogeswaranL18,
......@@ -1377,7 +1383,7 @@
Daum{\'e} III, Hal},
month = jul,
year = {2015},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {Association for Computational Linguistics},
pages = {1681--1691},
}
@inproceedings{DBLP:journals/corr/abs-1301-3781,
......@@ -1386,22 +1392,24 @@
Greg Corrado and
Jeffrey Dean},
title = {Efficient Estimation of Word Representations in Vector Space},
journal = {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}
author = {Quoc V. Le and
Tomas Mikolov},
title = {Distributed Representations of Sentences and Documents},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {32},
pages = {1188--1196},
publisher = {JMLR.org},
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},
publisher = {Association for Computational Linguistics},
year = {2017}
}
@inproceedings{DBLP:conf/emnlp/PenningtonSM14,
......@@ -1410,15 +1418,20 @@
Christopher D. Manning},
title = {Glove: Global Vectors for Word Representation},
pages = {1532--1543},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {{ACL}},
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}
author = {Ryan Kiros and
Yukun Zhu and
Ruslan Salakhutdinov and
Richard S. Zemel and
Raquel Urtasun and
Antonio Torralba and
Sanja Fidler},
title = {Skip-Thought Vectors},
pages = {3294--3302},
year = {2015}
}
@inproceedings{DBLP:conf/naacl/PetersNIGCLZ18,
author = {Matthew E. Peters and
......@@ -1430,7 +1443,7 @@
Luke Zettlemoyer},
title = {Deep Contextualized Word Representations},
pages = {2227--2237},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {Association for Computational Linguistics},
year = {2018}
}
@misc{radford2018improving,
......@@ -1448,15 +1461,16 @@
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}
author = {John S. White and
Theresa A. O'Connell and
Francis E. O'Mara},
title = {The {ARPA} {MT} Evaluation Methodologies: Evolution, Lessons, and
Future Approaches},
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}
}
......@@ -1467,7 +1481,7 @@
Gregory A. Sanders},
title = {The {NIST} 2008 Metrics for machine translation challenge - overview,
methodology, metrics, and results},
journal = {Machine Translation},
journal = {Mach. Transl.},
volume = {23},
number = {2-3},
pages = {71--103},
......@@ -1476,7 +1490,6 @@
@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,
......@@ -1487,7 +1500,7 @@
Josh Schroeder},
title = {(Meta-) Evaluation of Machine Translation},
pages = {136--158},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/wmt/Callison-BurchK12,
......@@ -1499,14 +1512,14 @@
Lucia Specia},
title = {Findings of the 2012 Workshop on Statistical Machine Translation},
pages = {10--51},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {The Association for Computer 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},
publisher = {The Association for Computer Linguistics},
year = {2012}
}
@inproceedings{DBLP:conf/wmt/BojarCFHHHKLMNP15,
......@@ -1526,14 +1539,14 @@
Marco Turchi},
title = {Findings of the 2015 Workshop on Statistical Machine Translation},
pages = {1--46},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {The Association for Computer 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},
publisher = {{ISCA}},
year = {2012}
}
@inproceedings{DBLP:conf/acl/LiuG05,
......@@ -1541,7 +1554,7 @@
Daniel Gildea},
title = {Syntactic Features for Evaluation of Machine Translation},
pages = {25--32},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {Association for Computational Linguistics},
year = {2005}
}
@inproceedings{DBLP:conf/wmt/GimenezM07a,
......@@ -1550,7 +1563,7 @@
title = {Linguistic Features for Automatic Evaluation of Heterogenous {MT}
Systems},
pages = {256--264},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {Association for Computational Linguistics},
year = {2007}
}
@article{DBLP:journals/mt/PadoCGJM09,
......@@ -1561,7 +1574,7 @@
Christopher D. Manning},
title = {Measuring machine translation quality as semantic equivalence: {A}
metric based on entailment features},
journal = {Machine Translation},
journal = {Mach. Transl.},
volume = {23},
number = {2-3},
pages = {181--193},
......@@ -1573,7 +1586,7 @@
Andy Way},
title = {Dependency-Based Automatic Evaluation for Machine Translation},
pages = {80--87},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {Association for Computational Linguistics},
year = {2007},
}
@inproceedings{DBLP:conf/wmt/OwczarzakGW07,
......@@ -1582,7 +1595,7 @@
Andy Way},
title = {Labelled Dependencies in Machine Translation Evaluation},
pages = {104--111},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {Association for Computational Linguistics},
year = {2007},
}
@inproceedings{DBLP:conf/coling/YuWXJLL14,
......@@ -1594,7 +1607,7 @@
Shouxun Lin},
title = {{RED:} {A} Reference Dependency Based {MT} Evaluation Metric},
pages = {2042--2051},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {{ACL}},
year = {2014}
}
@inproceedings{DBLP:conf/wmt/PopovicN09,
......@@ -1602,7 +1615,7 @@
Hermann Ney},
title = {Syntax-Oriented Evaluation Measures for Machine Translation Output},
pages = {29--32},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {Association for Computational Linguistics},
year = {2009}
}
@inproceedings{DBLP:conf/acl/BanchsL11,
......@@ -1610,13 +1623,12 @@
Haizhou Li},
title = {{AM-FM:} {A} Semantic Framework for Translation Quality Assessment},
pages = {153--158},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {The Association for Computer 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}
}
......@@ -1627,7 +1639,7 @@
Dekai Wu},
title = {{XMEANT:} Better semantic {MT} evaluation without reference translations},
pages = {765--771},
publisher = {Annual Meeting of the Association for Computational Linguistics},
publisher = {The Association for Computer Linguistics},
year = {2014}
}
@inproceedings{DBLP:conf/lrec/VilarXDN06,
......@@ -1643,7 +1655,6 @@
@inproceedings{popovic2011human,
title={From human to automatic error classification for machine translation output},
author={Popovic, Maja and Burchardt, Aljoscha and others},
booktitle={European Association for Machine Translation},
year={2011}
}
@article{DBLP:journals/mt/CostaLLCC15,
......@@ -1654,7 +1665,7 @@
Lu{\'{\i}}sa Coheur},
title = {A linguistically motivated taxonomy for Machine Translation error
analysis},
journal = {Machine Translation},
journal = {Mach. Transl.},
volume = {29},
number = {2},
pages = {127--161},
......@@ -1663,7 +1674,6 @@
@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}
}
......@@ -1679,7 +1689,7 @@
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},
publisher = {Association for Computational Linguistics},
year = {2006}
}
@inproceedings{DBLP:conf/wmt/PopovicN07,
......@@ -1688,7 +1698,7 @@
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},
publisher = {Association for Computational Linguistics},
year = {2007}
}
@inproceedings{DBLP:conf/acl/GonzalezMM13,
......@@ -1698,18 +1708,19 @@
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},
publisher = {The Association for Computer Linguistics},
year = {2013}
}
@inproceedings{coughlin2003correlating,
title={Correlating automated and human assessments of machine translation quality},
author={Coughlin, Deborah},
year={2003}
pages={63--70},
year={2003},
organization={Citeseer}
}
@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}
}
@article{pearson1920notes,
......@@ -1725,27 +1736,24 @@
@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}
}
@article{finch2004using,
title={Using a paraphraser to improve machine translation evaluation},
author={Finch, Andrew and Akiba, Yasuhiro and Sumita, Eiichiro},
journal={International Joint Conference on Natural Language Processing},
journal={Proceedings of IJCNLP-2004},
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}
......@@ -1753,7 +1761,6 @@
@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,
......@@ -1766,20 +1773,10 @@
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},
publisher = {{ACL}},
year = {2003},
}
@inproceedings{chen-guo-2015-representation,
title = "Representation Based Translation Evaluation Metrics",
author = "Chen, Boxing and Guo, Hongyu",
booktitle = "Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
year = "2015",
address = "Beijing, China",
publisher = "Association for Computational Linguistics",
pages = "150--155",
}
%%%%% chapter 4------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
......@@ -1832,6 +1829,171 @@
year ={1949},
publisher ={Wiley Online Library}
}
@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}
}
@article{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},
journal={中文信息学报},
volume={24},
number={110--116},
year={2010},
}
@article{2005Improving,
title={Improving Statistical Word Alignment with Ensemble Methods},
author={ Wu Hua and Wang Haifeng },
year={2005},
}
@article{1998Grammar,
title={Grammar Inference and Statistical Machine Translation},
author={Ye-Yi Wang and Jaime Carbonell},
year={1998},
}
@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},
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 = {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 = {The Association for Computational Linguistics},
year = {2013}
}
@article{DBLP:journals/coling/FraserM07,
author = {Alexander M. Fraser and
Daniel Marcu},
title = {Measuring Word Alignment Quality for Statistical Machine Translation},
journal = {Comput. Linguistics},
volume = {33},
number = {3},
pages = {293--303},
year = {2007}
}
@inproceedings{DBLP:conf/acl/DeNeroK07,
author = {John DeNero and
Dan Klein},
title = {Tailoring Word Alignments to Syntactic Machine Translation},
publisher = {The Association for Computational Linguistics},
year = {2007}
}
@inproceedings{paul2007all,
author = {Paul C Davis，Zhuli Xie and
Kevin Small},
publisher={暂时未找到},
title = {All Links are not the Same: Evaluating Word Alignments for Statistical Machine Translation},
year = {2007}
}
@article{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},
journal={中文信息学报},
volume={23},
number={88-94},
year={2009}
}
@article{DBLP:journals/coling/FraserM07,
author = {Alexander M. Fraser and
Daniel Marcu},
title = {Measuring Word Alignment Quality for Statistical Machine Translation},
journal = {Comput. Linguistics},
volume = {33},
number = {3},
pages = {293--303},
year = {2007}
}
@article{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},
journal = {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}
}
@article{DBLP:journals/mt/FlemingKN15,
author = {Noah Fleming and
Antonina Kolokolova and
Renesa Nizamee},
title = {Complexity of alignment and decoding problems: restrictions and approximations},
journal = {Mach. Transl.},
volume = {29},
number = {3-4},
pages = {163--187},
year = {2015}
}
%%%%% chapter 5------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
......
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