One Translation Per Discourse

We revisit the one sense per discourse hypothesis of Gale et al. in the context of machine translation. Since a given sense can be lexicalized differently in translation, do we observe one translation per discourse? Analysis of manual translations reveals that the hypothesis still holds when using translations in parallel text as sense annotation, thus confirming that translational differences represent useful sense distinctions. Analysis of Statistical Machine Translation (SMT) output showed that despite ignoring document structure, the one translation per discourse hypothesis is strongly supported in part because of the low variability in SMT lexical choice. More interestingly, cases where the hypothesis does not hold can reveal lexical choice errors. A preliminary study showed that enforcing the one translation per discourse constraint in SMT can potentially improve translation quality, and that SMT systems might benefit from translating sentences within their entire document context.

[1]  Srinivas Bangalore,et al.  Statistical Machine Translation through Global Lexical Selection and Sentence Reconstruction , 2007, ACL.

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

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

[4]  Hwee Tou Ng,et al.  Word Sense Disambiguation Improves Statistical Machine Translation , 2007, ACL.

[5]  Noah A. Smith,et al.  Rich Source-Side Context for Statistical Machine Translation , 2008, WMT@ACL.

[6]  Alon Lavie,et al.  METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments , 2005, IEEvaluation@ACL.

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

[8]  George R. Doddington,et al.  Automatic Evaluation of Machine Translation Quality Using N-gram Co-Occurrence Statistics , 2002 .

[9]  Roland Kuhn,et al.  Mixture-Model Adaptation for SMT , 2007, WMT@ACL.

[10]  Andreas Stolcke,et al.  SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

[11]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[12]  David Yarowsky,et al.  A method for disambiguating word senses in a large corpus , 1992, Comput. Humanit..

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

[14]  Lucia Specia,et al.  n-Best Reranking for the Efficient Integration of Word Sense Disambiguation and Statistical Machine Translation , 2008, CICLing.

[15]  Silvia Bernardini,et al.  A New Approach to the Study of Translationese: Machine-learning the Difference between Original and Translated Text , 2005, Lit. Linguistic Comput..

[16]  Robert Krovetz,et al.  More than One Sense Per Discourse , 1998 .

[17]  Andy Way,et al.  Exploiting source similarity for SMT using context-informed features , 2007, TMI.

[18]  Philipp Koehn,et al.  Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[19]  Philipp Koehn,et al.  Experiments in Domain Adaptation for Statistical Machine Translation , 2007, WMT@ACL.

[20]  Helmut Schmidt,et al.  Probabilistic part-of-speech tagging using decision trees , 1994 .

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

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

[23]  Marine Carpuat,et al.  Word Sense Disambiguation vs. Statistical Machine Translation , 2005, ACL.

[24]  Ted Pedersen,et al.  WordNet::Similarity - Measuring the Relatedness of Concepts , 2004, NAACL.

[25]  Marine Carpuat,et al.  Improving Statistical Machine Translation Using Word Sense Disambiguation , 2007, EMNLP.

[26]  Eneko Agirre,et al.  Word Sense Disambiguation using Conceptual Density , 1996, COLING.

[27]  David Yarowsky,et al.  Distinguishing systems and distinguishing senses: new evaluation methods for Word Sense Disambiguation , 1999, Natural Language Engineering.

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