Filtering Syntactic Constraints for Statistical Machine Translation

Source language parse trees offer very useful but imperfect reordering constraints for statistical machine translation. A lot of effort has been made for soft applications of syntactic constraints. We alternatively propose the selective use of syntactic constraints. A classifier is built automatically to decide whether a node in the parse trees should be used as a reordering constraint or not. Using this information yields a 0.8 BLEU point improvement over a full constraint-based system.

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

[2]  Hitoshi Isahara,et al.  An Error-Driven Word-Character Hybrid Model for Joint Chinese Word Segmentation and POS Tagging , 2009, ACL/IJCNLP.

[3]  Eiichiro Sumita,et al.  Dynamic Model Interpolation for Statistical Machine Translation , 2008, WMT@ACL.

[4]  Colin Cherry,et al.  Cohesive Phrase-Based Decoding for Statistical Machine Translation , 2008, ACL.

[5]  Yoram Singer,et al.  Pegasos: primal estimated sub-gradient solver for SVM , 2011, Math. Program..

[6]  Dekai Wu,et al.  Stochastic Inversion Transduction Grammars, with Application to Segmentation, Bracketing, and Alignment of Parallel Corpora , 1995, IJCAI.

[7]  Hailong Cao,et al.  Study on Architectures for Chinese POS Tagging and Parsing , 2008 .

[8]  Philip Resnik,et al.  Soft Syntactic Constraints for Hierarchical Phrased-Based Translation , 2008, ACL.

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

[10]  H. Isahara,et al.  Empirical study on Parsing Chinese Based on Collins ’ Model , 2007 .

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

[12]  Kevin Knight,et al.  Decoding Complexity in Word-Replacement Translation Models , 1999, Comput. Linguistics.

[13]  Kevin Knight,et al.  A Syntax-based Statistical Translation Model , 2001, ACL.

[14]  Victoria Fossum,et al.  Using Bilingual Chinese-English Word Alignments to Resolve PP-attachment Ambiguity in English , 2008, AMTA.

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

[16]  Eiichiro Sumita,et al.  Imposing Constraints from the Source Tree on ITG Constraints for SMT , 2008, SSST@ACL.

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

[18]  Yang Liu,et al.  Tree-to-String Alignment Template for Statistical Machine Translation , 2006, ACL.

[19]  Daniel Marcu,et al.  What’s in a translation rule? , 2004, NAACL.