A Systematic Comparison of Training Criteria for Statistical Machine Translation

We address the problem of training the free parameters of a statistical machine translation system. We show significant improvements over a state-of-the-art minimum error rate training baseline on a large ChineseEnglish translation task. We present novel training criteria based on maximum likelihood estimation and expected loss computation. Additionally, we compare the maximum a-posteriori decision rule and the minimum Bayes risk decision rule. We show that, not only from a theoretical point of view but also in terms of translation quality, the minimum Bayes risk decision rule is preferable.

[1]  William H. Press,et al.  Numerical recipes in C , 2002 .

[2]  Hermann Ney,et al.  Discriminative Training and Maximum Entropy Models for Statistical Machine Translation , 2002, ACL.

[3]  Hermann Ney.  Stochastic Modelling: From Pattern Classification to Language Translation , 2001, DDMMT@ACL.

[4]  John Cocke,et al.  A Statistical Approach to Machine Translation , 1990, CL.

[5]  Hermann Ney,et al.  N-Gram Posterior Probabilities for Statistical Machine Translation , 2006, WMT@HLT-NAACL.

[6]  Ashish Venugopal.  Training and Evaluating Error Minimization Rules for Statistical Machine Translation , 2005 .

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

[8]  Hermann Ney,et al.  The RWTH statistical machine translation system for the IWSLT 2006 evaluation , 2006, IWSLT.

[9]  Philipp Koehn,et al.  Re-evaluating the Role of Bleu in Machine Translation Research , 2006, EACL.

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

[11]  Chin-Yew Lin,et al.  ORANGE: a Method for Evaluating Automatic Evaluation Metrics for Machine Translation , 2004, COLING.

[12]  Alexander H. Waibel,et al.  Training and Evaluating Error Minimization Decision Rules for Statistical Machine Translation , 2005, ParallelText@ACL.

[13]  Joseph P. Turian,et al.  Evaluation of machine translation and its evaluation , 2003, MTSUMMIT.

[14]  Hermann Ney,et al.  Minimum Bayes Risk Decoding for BLEU , 2007, ACL.

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

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

[17]  David A. Smith,et al.  Minimum Risk Annealing for Training Log-Linear Models , 2006, ACL.

[18]  George R. Doddington,et al.  Automatic Evaluation of Machine Translation Quality Using N-gram Co-Occurrence Statistics , 2002 .

[19]  Anoop Sarkar,et al.  Discriminative Reranking for Machine Translation , 2004, NAACL.

[20]  Philipp Koehn,et al.  Pharaoh: A Beam Search Decoder for Phrase-Based Statistical Machine Translation Models , 2004, AMTA.

[21]  Shankar Kumar,et al.  Minimum Bayes-Risk Decoding for Statistical Machine Translation , 2004, NAACL.

[22]  Tong Zhang,et al.  A Discriminative Global Training Algorithm for Statistical MT , 2006, ACL.