Encouraging Consistent Translation Choices

It has long been observed that monolingual text exhibits a tendency toward "one sense per discourse," and it has been argued that a related "one translation per discourse" constraint is operative in bilingual contexts as well. In this paper, we introduce a novel method using forced decoding to confirm the validity of this constraint, and we demonstrate that it can be exploited in order to improve machine translation quality. Three ways of incorporating such a preference into a hierarchical phrase-based MT model are proposed, and the approach where all three are combined yields the greatest improvements for both Arabic-English and Chinese-English translation experiments.

[1]  Stephen E. Robertson,et al.  Okapi at TREC-3 , 1994, TREC.

[2]  Stephen E. Robertson,et al.  GatfordCentre for Interactive Systems ResearchDepartment of Information , 1996 .

[3]  Philip Resnik,et al.  An Unsupervised Method for Word Sense Tagging using Parallel Corpora , 2002, ACL.

[4]  David Yarowsky,et al.  One Sense Per Discourse , 1992, HLT.

[5]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[6]  Marine Carpuat,et al.  One Translation Per Discourse , 2009, SEW@NAACL-HLT.

[7]  D. Brown.  Exploiting Document-Level Context for Data-Driven Machine Translation , 2008 .

[8]  Hwee Tou Ng,et al.  Exploiting Parallel Texts for Word Sense Disambiguation: An Empirical Study , 2003, ACL.

[9]  Hua Wu,et al.  Improving Statistical Machine Translation with Monolingual Collocation , 2010, ACL.

[10]  Marcello Federico,et al.  Domain Adaptation for Statistical Machine Translation with Monolingual Resources , 2009, WMT@EACL.

[11]  Yifan He,et al.  Consistent Translation using Discriminative Learning - A Translation Memory-inspired Approach , 2011, ACL.

[12]  Christof Monz,et al.  Statistical Machine Translation with Local Language Models , 2011, EMNLP.

[13]  David Chiang,et al.  A Hierarchical Phrase-Based Model for Statistical Machine Translation , 2005, ACL.

[14]  Hermann Ney,et al.  A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.

[15]  David Yarowsky,et al.  Unsupervised Word Sense Disambiguation Rivaling Supervised Methods , 1995, ACL.

[16]  Koby Crammer,et al.  Online Passive-Aggressive Algorithms , 2003, J. Mach. Learn. Res..

[17]  Jingbo Zhu,et al.  Document-level Consistency Verification in Machine Translation , 2011, MTSUMMIT.

[18]  Alex Waibel,et al.  Adaptation of the translation model for statistical machine translation based on information retrieval , 2005, EAMT.

[19]  Nizar Habash,et al.  Improved Arabic-to-English statistical machine translation by reordering post-verbal subjects for word alignment , 2010, Machine Translation.

[20]  Smaranda Muresan,et al.  Generalizing Word Lattice Translation , 2008, ACL.

[21]  Daniel Jurafsky,et al.  A Conditional Random Field Word Segmenter for Sighan Bakeoff 2005 , 2005, IJCNLP.

[22]  Joseph Olive,et al.  Handbook of Natural Language Processing and Machine Translation: DARPA Global Autonomous Language Exploitation , 2011 .

[23]  Lluís Màrquez i Villodre,et al.  Context-aware Discriminative Phrase Selection for Statistical Machine Translation , 2007, WMT@ACL.

[24]  Liu Li,et al.  Learning to Transform and Select Elementary Trees for Improved Syntax-based Machine Translations , 2011, ACL.

[25]  Shujian Huang,et al.  Language Model Weight Adaptation Based on Cross-entropy for Statistical Machine Translation , 2011, PACLIC.

[26]  Seth Kulick,et al.  Enhancing the Arabic Treebank: a Collaborative Effort toward New Annotation Guidelines , 2008, LREC.

[27]  David Chiang,et al.  Hierarchical Phrase-Based Translation , 2007, CL.

[28]  Stephan Vogel,et al.  Language Model Adaptation for Statistical Machine Translation via Structured Query Models , 2004, COLING.

[29]  Germán Sanchis-Trilles,et al.  Bayesian Adaptation for Statistical Machine Translation , 2010, SSPR/SPR.

[30]  Jörg Tiedemann,et al.  Context Adaptation in Statistical Machine Translation Using Models with Exponentially Decaying Cache , 2010, ACL 2010.