Paper: A Discriminative Global Training Algorithm For Statistical MT

ACL ID P06-1091
Title A Discriminative Global Training Algorithm For Statistical MT
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2006
Authors

This paper presents a novel training al- gorithm for a linearly-scored block se- quence translation model. The key com- ponent is a new procedure to directly op- timize the global scoring function used by a SMT decoder. No translation, language, or distortion model probabilities are used as in earlier work on SMT. Therefore our method, which employs less domain specific knowledge, is both simpler and more extensible than previous approaches. Moreover, the training procedure treats the decoder as a black-box, and thus can be used to optimize any decoding scheme. The training algorithm is evaluated on a standard Arabic-English translation task.