Accession Number:

ADA460576

Title:

Minimum Bayes-Risk Decoding for Statistical Machine Translation

Descriptive Note:

Corporate Author:

JOHNS HOPKINS UNIV BALTIMORE MD CENTER FOR LANGUAGE AND SPEECH PROCESSING (CLSP)

Personal Author(s):

Report Date:

2004-01-01

Pagination or Media Count:

9.0

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.

Subject Categories:

  • Linguistics
  • Anatomy and Physiology
  • Statistics and Probability

Distribution Statement:

APPROVED FOR PUBLIC RELEASE