Can Semantic Role Labeling Improve SMT?

We present a series of empirical studies aimed at illuminating more precisely the likely contribution of semantic roles in improving statistical machine translation accuracy. The experiments reported study several aspects key to success: (1) the frequencies of types of SMT errors where semantic parsing and role labeling could help, and (2) if and where semantic roles offer more accurate guidance to SMT than merely syntactic annotation, and (3) the potential quantitative impact of realistic semantic role guidance to SMT systems, in terms of BLEU and METEOR scores.

[1]  Lluís Màrquez i Villodre,et al.  A Smorgasbord of Features for Automatic MT Evaluation , 2008, WMT@ACL.

[2]  Daniel Gildea,et al.  The Proposition Bank: An Annotated Corpus of Semantic Roles , 2005, CL.

[3]  Alexander M. Fraser,et al.  A Smorgasbord of Features for Statistical Machine Translation , 2004, NAACL.

[4]  Pascale Fung,et al.  Automatic Learning of Chinese English Semantic Structure Mapping , 2006, 2006 IEEE Spoken Language Technology Workshop.

[5]  Daniel Jurafsky,et al.  Shallow Semantc Parsing of Chinese , 2004, HLT-NAACL.

[6]  Nianwen Xue,et al.  Automatic Semantic Role Labeling for Chinese Verbs , 2005, IJCAI.

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

[8]  Daniel Jurafsky,et al.  Automatic Labeling of Semantic Roles , 2002, CL.

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

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

[11]  Nianwen Xue,et al.  Semantic role labeling of nominalized predicates in Chinese , 2006, NAACL.

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

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

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

[15]  Dekai Wu,et al.  Proceedings of SSST-3, 3rd Workshop on Syntax and Structure in Statistical Translation , 2009, HLT-NAACL 2009.

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

[17]  Daniel Jurafsky,et al.  Support Vector Learning for Semantic Argument Classification , 2005, Machine Learning.

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

[19]  Lluís Màrquez i Villodre,et al.  Linguistic Features for Automatic Evaluation of Heterogenous MT Systems , 2007, WMT@ACL.

[20]  Marine Carpuat,et al.  HKUST statistical machine translation experiments for IWSLT 2007 , 2007, IWSLT.