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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2004
- Accession Number
- ADA460576
Entities
People
- Shankar Kumar
- William Byrne
Organizations
- Johns Hopkins University