Paper: An Empirical Study of Translation Rule Extraction with Multiple Parsers

ACL ID C10-2154
Title An Empirical Study of Translation Rule Extraction with Multiple Parsers
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

Translation rule extraction is an impor- tant issue in syntax-based Statistical Ma- chine Translation (SMT). Recent studies show that rule coverage is one of the key factors affecting the success of syntax- based systems. In this paper, we first present a simple and effective method to improve rule coverage by using multiple parsers in translation rule extraction, and then empirically investigate the effec- tiveness of our method on Chinese- English translation tasks. Experimental results show that extracting translation rules using multiple parsers improves a string-to-tree system by over 0.9 BLEU points on both NIST 2004 and 2005 test corpora.