Paper: A Localized Prediction Model For Statistical Machine Translation

ACL ID P05-1069
Title A Localized Prediction Model For Statistical Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2005
Authors

In this paper, we present a novel training method for a localized phrase-based predic- tion model for statistical machine translation (SMT). The model predicts blocks with orien- tation to handle local phrase re-ordering. We use a maximum likelihood criterion to train a log-linear block bigram model which uses real- valued features (e.g. a language model score) as well as binary features based on the block identities themselves, e.g. block bigram fea- tures. Our training algorithm can easily handle millions of features. The best system obtains a a2a4a3a6a5a7 % improvement over the baseline on a standard Arabic-English translation task.