Dependency Relations as Source Context in Phrase-Based SMT

The Phrase-Based Statistical Machine Translation (PB-SMT) model has recently begun to include source context modeling, under the assumption that the proper lexical choice of an ambiguous word can be determined from the context in which it appears. Various types of lexical and syntactic features such as words, parts-of-speech, and supertags have been explored as effective source context in SMT. In this paper, we show that position-independent syntactic dependency relations of the head of a source phrase can be modeled as useful source context to improve target phrase selection and thereby improve overall performance of PB-SMT. On a Dutch—English translation task, by combining dependency relations and syntactic contextual features (part-of-speech), we achieved a 1.0 BLEU (Papineni et al., 2002) point improvement (3.1% relative) over the baseline.

[1]  Michael Collins,et al.  A Discriminative Model for Tree-to-Tree Translation , 2006, EMNLP.

[2]  Marc Dymetman,et al.  Learning Machine Translation , 2010 .

[3]  Franz Josef Och,et al.  Minimum Error Rate Training in Statistical Machine Translation , 2003, ACL.

[4]  Robert L. Mercer,et al.  A Statistical Approach to Sense Disambiguation in Machine Translation , 1991, HLT.

[5]  Matthew G. Snover,et al.  A Study of Translation Edit Rate with Targeted Human Annotation , 2006, AMTA.

[6]  Andy Way,et al.  Syntactically Lexicalized Phrase-Based SMT , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[7]  Walter Daelemans,et al.  An efficient memory-based morphosyntactic tagger and parser for Dutch , 2007, CLIN 2007.

[8]  Marine Carpuat,et al.  Context-dependent phrasal translation lexicons for statistical machine translation , 2007, MTSUMMIT.

[9]  Walter Daelemans,et al.  A feature-relevance heuristic for indexing and compressing large case bases , 1997 .

[10]  Cyril Goutte.  Automatic Evaluation of Machine Translation Quality , 2006 .

[11]  Walter Daelemans,et al.  Memory-Based Language Processing , 2009, Studies in natural language processing.

[12]  Jesús Giménez,et al.  Discriminative Phrase Selection for SMT , 2008 .

[13]  Hermann Ney,et al.  Refined Lexicon Models for Statistical Machine Translation using a Maximum Entropy Approach , 2001, ACL.

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

[15]  Ralph Weischedel,et al.  A STUDY OF TRANSLATION ERROR RATE WITH TARGETED HUMAN ANNOTATION , 2005 .

[16]  Daniel Marcu,et al.  Statistical Phrase-Based Translation , 2003, NAACL.

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

[18]  Hermann Ney,et al.  Discriminative Training and Maximum Entropy Models for Statistical Machine Translation , 2002, ACL.

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

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

[21]  Hermann Ney,et al.  Improvements in Phrase-Based Statistical Machine Translation , 2004, NAACL.

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

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

[24]  Daphne Koller,et al.  Word-Sense Disambiguation for Machine Translation , 2005, HLT.

[25]  Robert L. Mercer,et al.  The Mathematics of Statistical Machine Translation: Parameter Estimation , 1993, CL.

[26]  Yanjun Ma,et al.  Using Supertags as Source Language Context in SMT , 2009, EAMT.

[27]  Ben Taskar,et al.  An End-to-End Discriminative Approach to Machine Translation , 2006, ACL.

[28]  Marine Carpuat,et al.  Evaluating the Word Sense Disambiguation Performance of Statistical Machine Translation , 2005, IJCNLP.

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

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

[31]  Philippe Langlais,et al.  Explorations in using grammatical dependencies for contextual phrase translation disambiguation , 2008, EAMT.

[32]  Hermann Ney,et al.  Triplet Lexicon Models for Statistical Machine Translation , 2008, EMNLP.

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

[34]  Adam L. Berger,et al.  A Maximum Entropy Approach to Natural Language Processing , 1996, CL.