
FOLLOWUS
1.Software School, Xiamen University, Xiamen 361005, China
2.Center for Digital Media Computing, Xiamen University, Xiamen 361005, China
3.Cognitive Science Department, Xiamen University, Xiamen 361005, China
4.Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
[ "Jin-song SU, E-mail: jssu@xmu.edu.cn" ]
收稿:2013-08-04,
修回:2014-;2-19,
纸质出版:2014-04
Scan QR Code
主题敏感的枢轴语言统计机器翻译[J]. 信息与电子工程前沿(英文), 2014,15(4):241-253.
Jin-song SU, Xiao-dong SHI, Yan-zhou HUANG, et al. Topic-aware pivot language approach for statistical machine translation[J]. Frontiers of Information Technology & Electronic Engineering, 2014, 15(4): 241-253.
主题敏感的枢轴语言统计机器翻译[J]. 信息与电子工程前沿(英文), 2014,15(4):241-253. DOI: 10.1631/jzus.C1300208.
Jin-song SU, Xiao-dong SHI, Yan-zhou HUANG, et al. Topic-aware pivot language approach for statistical machine translation[J]. Frontiers of Information Technology & Electronic Engineering, 2014, 15(4): 241-253. DOI: 10.1631/jzus.C1300208.
研究目的
2
枢轴语言方法是解决统计机器翻译建模缺乏双语训练语言的一种方法。传统的枢轴语言方法忽视了枢轴语言文本存在的歧义性,导致建模得到的翻译模型概率知识不够准确。为此,本文使用主题模型为不同层次的上下文信息进行建模,并将上下文信息融入枢轴语言统计机器翻译的建模过程,以改善基于枢轴语言的统计机器翻译模型。
创新要点
2
使用传统的向量空间模型表示上下文,具有数据稀疏的缺点。本文采用主题模型将不同层次上下文信息概率化,使得枢轴语言文本的上下文信息能够较好融入翻译模型的概率计算,进而改善翻译模型。
研究方法
2
发挥主题模型的优势,使用主题模型对不同层次上下文进行降维表示;修改传统枢轴语言方法的建模公式,将上下文作为隐变量或相似度,重新调整翻译模型概率。
重要结论
2
数据实验表明,主题模型能够较好地表示不同层次的上下文,融入主题模型上下文的枢轴语言统计机器翻译模型比传统枢轴语言方法建立的模型具有更好效果。
The pivot language approach for statistical machine translation (SMT) is a good method to break the resource bottleneck for certain language pairs. However
in the implementation of conventional approaches
pivotside context information is far from fully utilized
resulting in erroneous estimations of translation probabilities. In this study
we propose two topic-aware pivot language approaches to use different levels of pivot-side context. The first method takes advantage of document-level context by assuming that the bridged phrase pairs should be similar in the document-level topic distributions. The second method focuses on the effect of local context. Central to this approach are that the phrase sense can be reflected by local context in the form of probabilistic topics
and that bridged phrase pairs should be compatible in the latent sense distributions. Then
we build an interpolated model bringing the above methods together to further enhance the system performance. Experimental results on French-Spanish and French-German translations using English as the pivot language demonstrate the effectiveness of topic-based context in pivot-based SMT.
N. Bertoldi , , , M. Federico . . Domain adaptation for statistical machine translation with monolingual resources . . Proc. 4th Workshop on Statistical Machine Translation , , 2009 . . p.182 - - 189 . . DOI: 10.3115/1626431.1626468 http://doi.org/10.3115/1626431.1626468 . .
N. Bertoldi , , , M. Barbaiani , , , M. Federico , , , 等 . . Phrase-based statistical machine translation with pivot languages . . Proc. Int. Workshop on Spoken Language Translation , , 2008 . . p.143 - - 149 . . . .
D.M. Blei , , , A.Y. Ng , , , M.I. Jordan . . Latent Dirichlet allocation . . J. Mach. Learn. Res. , , 2003 . . 3 993 - - 1022 . . . .
L. Borin . . You'll take the high road and I'll take the low road: using a third language to improve bilingual word alignment . . Proc. 18th Conf. on Computational Linguistics , , 2000 . . p.97 - - 103 . . DOI: 10.3115/990820.990835 http://doi.org/10.3115/990820.990835 . .
C. Callison-Burch , , , P. Koehn , , , M. Osborne . . Improved statistical machine translation using paraphrases . . Proc. Main Conf. on Human Language Technology Conf. of the North American Chapter of the Association of Computational Linguistics , , 2006 . . p.17 - - 24 . . DOI: 10.3115/1220835.1220838 http://doi.org/10.3115/1220835.1220838 . .
B.X. Chen , , , G. Foster , , , R. Kuhn . . Bilingual sense similarity for statistical machine translation . . Proc. 48th Annual Meeting of the Association for Computational Linguistics , , 2010 . . p.834 - - 843 . . . .
J.H. Clark , , , C. Dyer , , , A. Lavie , , , 等 . . Better hypothesis testing for statistical machine translation: controlling for optimizer instability . . Proc. 49th Annual Meeting of the Association for Computational Linguistics , , 2011 . . p.176 - - 181 . . . .
T. Cohn , , , M. Lapata . . Machine translation by triangulation: making effective use of multi-parallel corpora . . Proc. 45th Annual Meeting of the Association for Computational Linguistics , , 2007 . . p.728 - - 735 . . . .
M.R. Costa-Jussà , , , C. Henríquez , , , R.E. Banchs . . Enhancing scarce-resource language translation through pivot combinations . . Proc. 5th Int. Joint Conf. on Natural Language Processing , , 2011 . . p.1361 - - 1365 . . . .
J.M. Crego , , , A. Max , , , F. Yvon . . Local lexical adaptation in machine translation through triangulation: SMT helping SMT . . Proc. 23rd Int. Conf. on Computational Linguistics , , 2010 . . p.232 - - 240 . . . .
A. de Gispert , , , J.B. Mariño . . Catalan-English statistical machine translation without parallel corpus: bridging through Spanish . . Proc. 5th Int. Conf. on Language Resources and Evaluation , , 2006 . . p.65 - - 68 . . . .
M. Denkowski , , , A. Lavie . . Meteor 1.3: automatic metric for reliable optimization and evaluation of machine translation systems . . Proc. 6th Workshop on Statistical Machine Translation , , 2011 . . p.85 - - 91 . . . .
G. Dinu , , , M. Lapata . . Measuring distributional similarity in context . . Proc. Conf. on Empirical Methods in Natural Language Processing , , 2010 . . p.1162 - - 1172 . . . .
K. Filali , , , J. Bilmes . . Leveraging multiple languages to improve statistical MT word alignments . . Proc. IEEE Automatic Speech Recognition and Understanding Workshop , , 2005 . . p.92 - - 97 . . . .
Z.X. Gong , , , G.D. Zhou , , , L.Y. Li . . Improve SMT with source-side "topic-document" distributions . . Proc. 13th Machine Translation Summit , , 2011 . . p.496 - - 502 . . . .
T.L. Griffiths , , , M. Steyvers . . Finding scientific topics . . PNAS , , 2004 . . p.90 - - 95 . . . .
N. Habash , , , J. Hu . . Improving Arabic-Chinese statistical machine translation using English as pivot language . . Proc. 4th Workshop on Statistical Machine Translation , , 2009 . . p.173 - - 181 . . . .
Z.J. He , , , Q. Liu , , , S.X. Lin . . Improving statistical machine translation using lexicalized rule selection . . Proc. 22nd Int. Conf. on Computational Linguistics , , 2008 . . p.321 - - 328 . . . .
A.S. Hildebrand , , , M. Eck , , , S. Vogel , , , 等 . . Adaptation of the translation model for statistical machine translation based on information retrieval . . EAMT 10th Annual Conf. , , 2005 . . p.133 - - 142 . . . .
M. Huck , , , H. Ney . . Pivot lightly-supervised training for statistical machine translation . . Proc. 10th Conf. of the Association for Machine Translation in the Americas , , 2012 . . p.50 - - 57 . . . .
M. Khalilov , , , M.R. Costa-Jussà , , , C.A. Henríquez , , , 等 . . The TALP&I2R SMT sytstems for IWSLT 2008 . . Proc. Int. Workshop on Spoken Language Translation , , 2008 . . p.116 - - 123 . . . .
P. Koehn . . Statistical significance tests for machine translation evaluation . . Proc. Conf. on Empirical Methods in Natural Language Processing , , 2004 . . p.388 - - 395 . . . .
P. Koehn , , , F.J. Och , , , D. Marcu . . Statistical phrasebased translation . . Proc. Conf. of the North American Chapter of the Association for Computational Linguistics , , 2003 . . p.48 - - 54 . . DOI: 10.3115/1073445.1073462 http://doi.org/10.3115/1073445.1073462 . .
S. Kumar , , , F.J. Och , , , W. Macherey . . Improving word alignment with bridge languages . . Proc. Joint Conf. on Empirical Methods in Natural Language Processing and Computational Natural Language Learning , , 2007 . . p.42 - - 50 . . . .
A. Mauser , , , S. Hasan , , , H. Ney . . Extending statistical machine translation with discriminative and triggerbased lexicon models . . Proc. Conf. on Empirical Methods in Natural Language Processing , , 2009 . . p.210 - - 218 . . . .
F.J. Och . . Minimum error rate training in statistical machine translation . . Proc. 41st Annual Meeting on Association for Computational Linguistics , , 2003 . . p.160 - - 167 . . DOI: 10.3115/1075096.1075117 http://doi.org/10.3115/1075096.1075117 . .
F.J. Och , , , H. Ney . . A systematic comparison of various statistical alignment models . . Comput. Linguist. , , 2003 . . 29 ( ( 1 ): ): 19 - - 51 . . DOI: 10.1162/089120103321337421 http://doi.org/10.1162/089120103321337421 . .
K. Papineni , , , S. Roukos , , , T. Ward , , , 等 . . BLEU: a method for automatic evaluation of machine translation . . Proc. 40th Annual Meeting on Association for Computational Linguistics , , 2002 . . p.311 - - 318 . . DOI: 10.3115/1073083.1073135 http://doi.org/10.3115/1073083.1073135 . .
M. Paul , , , H. Yamamoto , , , E. Sumita , , , 等 . . On the importance of pivot language selection for statistical machine translation . . Proc. Annual Conf. of the North American Chapter of the Association for Computational Linguistics , , 2009 . . p.221 - - 224 . . . .
N. Ruiz , , , M. Federico . . Topic adaptation for lecture translation through bilingual latent semantic models . . Proc. 6th Workshop on Statistical Machine Translation , , 2011 . . p.294 - - 302 . . . .
H. Schwenk . . Investigations on large-scale lightlysupervised training for statistical machine translation . . Proc. Int. Workshop on Spoken Language Translation , , 2008 . . p.182 - - 189 . . . .
L.B. Shen , , , J.X. Xu , , , B. Zhang , , , 等 . . Effective use of linguistic and contextual information for statistical machine translation . . Proc. Conf. on Empirical Methods in Natural Language Processing , , 2009 . . p.72 - - 80 . . . .
A. Stolcke . . SRILM - an extensible language modeling toolkit . . Proc. 7th Int. Conf. on Spoken Language Processing , , 2002 . . p.901 - - 904 . . . .
J.S. Su , , , H. Wu , , , H.F. Wang , , , 等 . . Translation model adaptation for statistical machine translation with monolingual topic information . . Proc. 50th Annual Meeting of the Association for Computational Linguistics , , 2012 . . p.459 - - 468 . . . .
Y.C. Tam , , , I. Lane , , , T. Schultz . . Bilingual LSA-based adaptation for statistical machine translation . . Mach. Transl. , , 2007 . . 21 ( ( 4 ): ): 187 - - 207 . . DOI: 10.1007/s10590-008-9045-2 http://doi.org/10.1007/s10590-008-9045-2 . .
R. Tanaka , , , Y. Murakami , , , T. Ishida . . Context-based approach for pivot translation services . . Proc. 21st Int. Joint Conf. on Artificial Intelligence , , 2009 . . p.1555 - - 1561 . . . .
N. Ueffing , , , G. Haffari , , , A. Sarkar . . Semi-supervised model adaptation for statistical machine translation . . Mach. Transl. , , 2007 . . 21 ( ( 2 ): ): 77 - - 94 . . DOI: 10.1007/s10590-008-9036-3 http://doi.org/10.1007/s10590-008-9036-3 . .
M. Utiyama , , , H. Isahara . . A comparison of pivot methods for phrase-based statistical machine translation . . Proc. Annual Conf. of the North American Chapter of the Association for Computational Linguistics , , 2007 . . p.484 - - 491 . . . .
H.F. Wang , , , H. Wu , , , Z.Y. Liu . . Word alignment for languages with scarce resources using bilingual corpora of other language pairs . . Proc. 21st Int. Conf. on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics , , 2006 . . p.874 - - 881 . . . .
H. Wu , , , H.F. Wang . . Pivot language approach for phrase-based statistical machine translation . . Mach. Transl. , , 2007 . . 21 ( ( 3 ): ): 165 - - 181 . . DOI: 10.1007/s10590-008-9041-6 http://doi.org/10.1007/s10590-008-9041-6 . .
H. Wu , , , H.F. Wang . . Revisiting pivot language approach for machine translation . . Proc. Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th Int. Joint Conf. on Natural Language Processing , , 2009 . . p.154 - - 162 . . . .
X.Y. Xiao , , , D.Y. Xiong , , , M. Zhang , , , 等 . . A topic similarity model for hierarchical phrase-based translation . . Proc. 50th Annual Meeting of the Association for Computational Linguistics , , 2012 . . p.750 - - 758 . . . .
Y. Zhang , , , S. Vogel , , , A. Waibel . . Interpreting BLEU/NIST scores: how much improvement do we need to have a better system? . . Proc. 4th Int. Conf. on Language Resources and Evaluation , , 2004 . . p.2051 - - 2054 . . . .
B. Zhao , , , E.P. Xing . . BiTAM: bilingual topic AdMixture models for word alignment . . Proc. 21st Int. Conf. on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics , , 2006 . . p.969 - - 976 . . . .
B. Zhao , , , E.P. Xing . . HM-BiTAM: bilingual topic exploration, word alignment, and translation . . Proc. Advances in Neural Information Processing Systems , , 2007 . . p.1689 - - 1696 . . . .
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621