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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2004
Accession Number
ADA460576

Entities

People

  • Shankar Kumar
  • William Byrne

Organizations

  • Johns Hopkins University

Tags

DTIC Thesaurus Topics

  • Applied Computer Science
  • Chinese Language
  • Computational Linguistics
  • Computational Science
  • Computations
  • Computer Science
  • Decoding
  • Hierarchies
  • Language
  • Linguistics
  • Machine Translation
  • Message Processing
  • Natural Language Processing
  • Natural Languages
  • Test Sets
  • Training
  • Translations

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Computational Modeling and Simulation
  • Computer Programming and Software Development.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Translation