Date of Original Version

10-2010

Type

Conference Proceeding

Journal Title

Proceedings of the Ninth Biennial Conference of the Association for Machine Translation in the Americas

Rights Management

Copyright 2010 AMTA

Abstract or Description

System combination exploits differences between machine translation systems to form a combined translation from several system outputs. Core to this process are features that reward n-gram matches between a candidate combination and each system output. Systems differ in performance at the n-gram level despite similar overall scores. We therefore advocate a new feature formulation: for each system and each small n, a feature counts n-gram matches between the system and candidate. We show post-evaluation improvement of 6.67 BLEU over the best system on NIST MT09 Arabic-English test data. Compared to a baseline system combination scheme from WMT 2009, we show improvement in the range of 1 BLEU point.

Share

COinS
 

Published In

Proceedings of the Ninth Biennial Conference of the Association for Machine Translation in the Americas.