论文信息 - Minimum Bayes-Risk decoding extended with similar examples: NAIST-NICT at IWSLT 2012

Minimum Bayes-Risk decoding extended with similar examples: NAIST-NICT at IWSLT 2012

This paper describes our methods used in the NAIST-NICT submission to the International Workshop on Spoken Language Translation (IWSLT) 2012 evaluation campaign. In particular, we propose two extensions to minimum bayesrisk decoding which reduces a expected loss.

Satoshi Nakamura | Masao Utiyama | Eiichiro Sumita | Hiroaki Shimizu

[1] Mo Yu,et al. Locally Training the Log-Linear Model for SMT , 2012, EMNLP.

[2] Daniel Jurafsky,et al. A Conditional Random Field Word Segmenter for Sighan Bakeoff 2005 , 2005, IJCNLP.

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

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

[5] Masao Utiyama,et al. Two methods for stabilizing MERT: NICT at IWSLT 2009 , 2009, IWSLT.

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

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

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

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

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

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