Automatic Post-Editing for the DiscoMT Pronoun Translation Task

This paper describes an automated postediting submission to the DiscoMT 2015 shared task on pronoun translation. Postediting is achieved by applying pronounspecific rules to the output of an Englishto-French phrase-based SMT system.

[1]  Preslav Nakov,et al.  Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation , 2015, DiscoMT@EMNLP.

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

[3]  David Yarowsky,et al.  NADA: A Robust System for Non-referential Pronoun Detection , 2011, DAARC.

[4]  Heeyoung Lee,et al.  A Multi-Pass Sieve for Coreference Resolution , 2010, EMNLP.

[5]  Jochen Weiner,et al.  Pronominal Anaphora in Machine Translation , 2014 .

[6]  Benoît Sagot,et al.  The Lefff, a Freely Available and Large-coverage Morphological and Syntactic Lexicon for French , 2010, LREC.

[7]  Heeyoung Lee,et al.  Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task , 2011, CoNLL Shared Task.

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

[9]  Rudolf Rosa,et al.  Two-step translation with grammatical post-processing , 2011, WMT@EMNLP.

[10]  Lena Schwartz.  French Grammar And Usage , 2016 .

[11]  Kenneth Heafield,et al.  KenLM: Faster and Smaller Language Model Queries , 2011, WMT@EMNLP.

[12]  Rosa Rudolf,et al.  Depfix, a Tool for Automatic Rule-based Post-editing of SMT , 2014, Prague Bull. Math. Linguistics.

[13]  Jörg Tiedemann,et al.  ParCor 1.0: A Parallel Pronoun-Coreference Corpus to Support Statistical MT , 2014, LREC.

[14]  Roger Hawkins,et al.  French Grammar and Usage , 1997 .