Statistical Post-Editing for a Statistical MT System

Statistical post-editing (SPE) techniques have been successfully applied to the output of Rule Based MT (RBMT) systems. In this paper we investigate the impact of SPE on a standard Phrase-Based Statistical Machine Translation (PB-SMT) system, using PB-SMT both for the first-stage MT and the second stage SPE system. Our results show that, while a naive approach to using SPE in a PB-SMT pipeline produces no or only modest improvements, a novel combination of source context modelling and thresholding can produce statistically significant improvements of 2 BLEU points over baseline using technical translation data for French to English.

[1]  K. J. Evans,et al.  Computer Intensive Methods for Testing Hypotheses: An Introduction , 1990 .

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

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

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

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

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

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

[8]  Andy Way,et al.  A cluster-based representation for multi-system MT evaluation , 2007 .

[9]  EHARA Terumasa,et al.  Rule based machine translation combined with statistical post editor for Japanese to English patent translation , 2007, MTSUMMIT.

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

[11]  Michel Simard,et al.  Statistical Phrase-Based Post-Editing , 2007, NAACL.

[12]  Cyril Goutte,et al.  Domain adaptation of MT systems through automatic post-editing , 2007, MTSUMMIT.

[13]  Philipp Koehn,et al.  Statistical Post-Editing on SYSTRAN‘s Rule-Based Translation System , 2007, WMT@ACL.

[14]  Kemal Oflazer,et al.  Exploring Different Representational Units in English-to-Turkish Statistical Machine Translation , 2007, WMT@ACL.

[15]  G. Roberts.  Computer Intensive Methods , 2007 .

[16]  Philipp Koehn,et al.  Findings of the 2009 Workshop on Statistical Machine Translation , 2009, WMT@EACL.

[17]  Philipp Koehn,et al.  Statistical Post Editing and Dictionary Extraction: Systran/Edinburgh Submissions for ACL-WMT2009 , 2009, WMT@EACL.

[18]  Yifan He,et al.  Consistent Translation using Discriminative Learning - A Translation Memory-inspired Approach , 2011, ACL.