Minimum Bayes-Risk Decoding for Statistical Machine Translation

Abstract : We present Minimum Bayes-Risk (MBR) decoding for statistical machine translation. This statistical approach aims to minimize expected loss of translation errors under loss functions that measure translation performance. We describe a hierarchy of loss functions that incorporate different levels of linguistic information from word strings, word-to-word alignments from an MT system, and syntactic structure from parse-trees of source and target language sentences. We report the performance of the MBR decoders on a Chinese-to-English translation task. Our results show that MBR decoding can be used to tune statistical MT performance for specific loss functions.

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

[2]  Michael Collins,et al.  New Ranking Algorithms for Parsing and Tagging: Kernels over Discrete Structures, and the Voted Perceptron , 2002, ACL.

[3]  Vaibhava Goel,et al.  Minimum Bayes-risk automatic speech recognition , 2000, Comput. Speech Lang..

[4]  I. Dan Melamed,et al.  Precision and Recall of Machine Translation , 2003, NAACL.

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

[6]  Franz Josef Och,et al.  Statistical machine translation: from single word models to alignment templates , 2002 .

[7]  Min Tang,et al.  Active Learning for Statistical Natural Language Parsing , 2002, ACL.

[8]  Hermann Ney,et al.  Generation of Word Graphs in Statistical Machine Translation , 2002, EMNLP.

[9]  Michael Collins,et al.  Head-Driven Statistical Models for Natural Language Parsing , 2003, CL.

[10]  Joshua Goodman,et al.  Parsing Algorithms and Metrics , 1996, ACL.

[11]  Srinivas Bangalore,et al.  Bootstrapping Bilingual Data using Consensus Translation for a Multilingual Instant Messaging System , 2002, COLING.

[12]  Alexander M. Fraser,et al.  Syntax for Statistical Machine Translation , 2003 .

[13]  Carolyn Pillers Dobler,et al.  Mathematical Statistics , 2002 .

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

[15]  George F. Foster,et al.  User-Friendly Text Prediction For Translators , 2002, EMNLP.

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

[17]  Shankar Kumar,et al.  Minimum Bayes-Risk Word Alignments of Bilingual Texts , 2002, EMNLP.

[18]  Shankar Kumar,et al.  A Weighted Finite State Transducer Implementation of the Alignment Template Model for Statistical Machine Translation , 2003, NAACL.

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

[20]  David Chiang,et al.  Two Statistical Parsing Models Applied to the Chinese Treebank , 2000, ACL 2000.