Consistent Translation using Discriminative Learning - A Translation Memory-inspired Approach

We present a discriminative learning method to improve the consistency of translations in phrase-based Statistical Machine Translation (SMT) systems. Our method is inspired by Translation Memory (TM) systems which are widely used by human translators in industrial settings. We constrain the translation of an input sentence using the most similar 'translation example' retrieved from the TM. Differently from previous research which used simple fuzzy match thresholds, these constraints are imposed using discriminative learning to optimise the translation performance. We observe that using this method can benefit the SMT system by not only producing consistent translations, but also improved translation outputs. We report a 0.9 point improvement in terms of BLEU score on English--Chinese technical documents.

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

[2]  Jean Carletta,et al.  Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization , 2005, ACL 2005.

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

[4]  Vladimir I. Levenshtein,et al.  Binary codes capable of correcting deletions, insertions, and reversals , 1965 .

[5]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[6]  Philipp Koehn,et al.  Convergence of Translation Memory and Statistical Machine Translation , 2010, JEC.

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

[8]  Yifan He,et al.  Bridging SMT and TM with Translation Recommendation , 2010, ACL.

[9]  Adam Lopez.  Tera-Scale Translation Models via Pattern Matching , 2008, COLING.

[10]  Josef van Genabith,et al.  Seeding Statistical Machine Translation with Translation Memory Output through Tree-Based Structural Alignment , 2010, SSST@COLING.

[11]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

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

[13]  Hsuan-Tien Lin,et al.  A note on Platt’s probabilistic outputs for support vector machines , 2007, Machine Learning.

[14]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[15]  J. Smith,et al.  EBMT for SMT : A New EBMT-SMT Hybrid , 2009 .

[16]  Hermann Ney,et al.  Improved backing-off for M-gram language modeling , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

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

[18]  Andy Way,et al.  Labelled Dependencies in Machine Translation Evaluation , 2007, WMT@ACL.

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

[20]  P. Isabelle,et al.  Phrase-based Machine Translation in a Computer-assisted Translation Environment , 2009, MTSUMMIT.

[21]  Lucia Specia,et al.  Improving the Confidence of Machine Translation Quality Estimates , 2009, MTSUMMIT.

[22]  Ralph Weischedel,et al.  A STUDY OF TRANSLATION ERROR RATE WITH TARGETED HUMAN ANNOTATION , 2005 .

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

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

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

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

[27]  Marc Dymetman,et al.  Dynamic Translation Memory: Using Statistical Machine Translation to Improve Translation Memory Fuzzy Matches , 2008, CICLing.