Paper: Minimum Error Rate Training In Statistical Machine Translation

ACL ID P03-1021
Title Minimum Error Rate Training In Statistical Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2003
Authors

Often, the training procedure for statisti- cal machine translation models is based on maximum likelihood or related criteria. A general problem of this approach is that there is only a loose relation to the final translation quality on unseen text. In this paper, we analyze various training criteria which directly optimize translation qual- ity. These training criteria make use of re- cently proposed automatic evaluation met- rics. We describe a new algorithm for effi- cient training an unsmoothed error count. We show that significantly better results can often be obtained if the final evalua- tion criterion is taken directly into account as part of the training procedure.