Sciweavers

ACL
2003

Minimum Error Rate Training in Statistical Machine Translation

14 years 1 months ago
Minimum Error Rate Training in Statistical Machine Translation
Often, the training procedure for statistical 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 quality. These training criteria make use of recently proposed automatic evaluation metrics. We describe a new algorithm for efficient training an unsmoothed error count. We show that significantly better results can often be obtained if the final evaluation criterion is taken directly into account as part of the training procedure.
Franz Josef Och
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2003
Where ACL
Authors Franz Josef Och
Comments (0)