Soft Syntactic Constraints for Hierarchical Phrased-Based Translation

In adding syntax to statistical MT, there is a tradeoff between taking advantage of linguistic analysis, versus allowing the model to exploit linguistically unmotivated mappings learned from parallel training data. A number of previous efforts have tackled this tradeoff by starting with a commitment to linguistically motivated analyses and then nding appropriate ways to soften that commitment. We present an approach that explores the tradeoff from the other direction, starting with a context-free translation model learned directly from aligned parallel text, and then adding soft constituent-level constraints based on parses of the source language. We obtain substantial improvements in performance for translation from Chinese and Arabic to English.

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

[2]  Jason Eisner,et al.  Learning Non-Isomorphic Tree Mappings for Machine Translation , 2003, ACL.

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

[4]  Daniel Marcu,et al.  What Can Syntax-Based MT Learn from Phrase-Based MT? , 2007, EMNLP.

[5]  Daniel Marcu,et al.  SPMT: Statistical Machine Translation with Syntactified Target Language Phrases , 2006, EMNLP.

[6]  Philipp Koehn,et al.  CCG Supertags in Factored Statistical Machine Translation , 2007, WMT@ACL.

[7]  Philipp Koehn,et al.  Factored Translation Models , 2007, EMNLP.

[8]  Haizhou Li,et al.  Ordering Phrases with Function Words , 2007, ACL.

[9]  Andy Way,et al.  Wrapper Syntax for Example-Based Machine Translation , 2006 .

[10]  Stefan Riezler,et al.  Grammatical Machine Translation , 2006, NAACL.

[11]  F ChenStanley,et al.  An Empirical Study of Smoothing Techniques for Language Modeling , 1996, ACL.

[12]  Philipp Koehn,et al.  Statistical Significance Tests for Machine Translation Evaluation , 2004, EMNLP.

[13]  Heidi Fox,et al.  Phrasal Cohesion and Statistical Machine Translation , 2002, EMNLP.

[14]  Daniel Marcu,et al.  Binarizing Syntax Trees to Improve Syntax-Based Machine Translation Accuracy , 2007, EMNLP.

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

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

[17]  Andreas Zollmann,et al.  Syntax Augmented Machine Translation via Chart Parsing , 2006, WMT@HLT-NAACL.

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

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

[20]  Philipp Koehn,et al.  Clause Restructuring for Statistical Machine Translation , 2005, ACL.

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

[22]  Hermann Ney,et al.  Improved Statistical Alignment Models , 2000, ACL.

[23]  Dan Klein,et al.  Accurate Unlexicalized Parsing , 2003, ACL.

[24]  Florence Reeder,et al.  Corpus-based comprehensive and diagnostic MT evaluation: initial Arabic, Chinese, French, and Spanish results , 2002 .

[25]  Daniel Marcu,et al.  Scalable Inference and Training of Context-Rich Syntactic Translation Models , 2006, ACL.

[26]  Dan Klein,et al.  Fast Exact Inference with a Factored Model for Natural Language Parsing , 2002, NIPS.

[27]  Dekai Wu,et al.  Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora , 1997, CL.

[28]  Chao Wang,et al.  Chinese Syntactic Reordering for Statistical Machine Translation , 2007, EMNLP.

[29]  Miles Osborne,et al.  Statistical Machine Translation , 2010, Encyclopedia of Machine Learning and Data Mining.

[30]  PietraVincent J. Della,et al.  The mathematics of statistical machine translation , 1993 .