Paper: Improving Statistical Machine Translation with Monolingual Collocation

ACL ID P10-1085
Title Improving Statistical Machine Translation with Monolingual Collocation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2010
Authors

This paper proposes to use monolingual collocations to improve Statistical Ma- chine Translation (SMT). We make use of the collocation probabilities, which are estimated from monolingual corpora, in two aspects, namely improving word alignment for various kinds of SMT sys- tems and improving phrase table for phrase-based SMT. The experimental re- sults show that our method improves the performance of both word alignment and translation quality significantly. As com- pared to baseline systems, we achieve ab- solute improvements of 2.40 BLEU score on a phrase-based SMT system and 1.76 BLEU score on a parsing-based SMT system.