Paper: Discriminative Alignment Training without Annotated Data for Machine Translation

ACL ID N07-2022
Title Discriminative Alignment Training without Annotated Data for Machine Translation
Venue Human Language Technologies
Session Short Paper
Year 2007
Authors

In present Statistical Machine Translation (SMT) systems, alignment is trained in a previous stage as the translation model. Consequently, alignment model parame- ters are not tuned in function of the trans- lation task, but only indirectly. In this paper, we propose a novel framework for discriminative training of alignment mod- els with automated translation metrics as maximization criterion. In this approach, alignments are optimized for the transla- tion task. In addition, no link labels at the word level are needed. This framework is evaluated in terms of automatic trans- lation evaluation metrics, and an improve- ment of translation quality is observed.