PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Minimum Bayes-risk System Combination
Jesús González Rubio, Alfons Juan and Francisco Casacuberta
In: ACL-HLT 2011(2011).

Abstract

We present minimum Bayes-risk system com- bination, a method that integrates consen- sus decoding and system combination into a unified multi-system minimum Bayes-risk (MBR) technique. Unlike other MBR meth- ods that re-rank translations of a single SMT system, MBR system combination uses the MBR decision rule and a linear combina- tion of the component systems’ probability distributions to search for the minimum risk translation among all the finite-length strings over the output vocabulary. We introduce ex- pected BLEU, an approximation to the BLEU score that allows to efficiently apply MBR in these conditions. MBR system combination is a general method that is independent of spe- cific SMT models, enabling us to combine systems with heterogeneous structure. Exper- iments show that our approach bring sig- nificant improvements to single-system-based MBR decoding and achieves comparable re- sults to different state-of-the-art system com- bination methods.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
ID Code:8785
Deposited By:Alfons Juan
Deposited On:21 February 2012