Paper: Two Easy Improvements to Lexical Weighting

ACL ID P11-2080
Title Two Easy Improvements to Lexical Weighting
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011

We introduce two simple improvements to the lexical weighting features of Koehn, Och, and Marcu (2003) for machine translation: one which smooths the probability of translating word f to word e by simplifying English mor- phology, and one which conditions it on the kind of training data that f and e co-occurred in.These new variations lead to improvements of up to +0.8 BLEU, with an average improve- ment of +0.6 BLEUacross two language pairs, two genres,and two translation systems.