Sciweavers

NAACL
2004

Minimum Bayes-Risk Decoding for Statistical Machine Translation

13 years 5 months ago
Minimum Bayes-Risk Decoding for Statistical Machine Translation
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.
Shankar Kumar, William J. Byrne
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2004
Where NAACL
Authors Shankar Kumar, William J. Byrne
Comments (0)