Discriminative word alignment via alignment matrix modeling

Abstract

In this paper a new discriminative word alignment method is presented. This approach models directly the alignment matrix by a conditional random field (CRF) and so no restrictions to the alignments have to be made. Furthermore, it is easy to add features and so all available information can be used. Since the structure of the CRFs can get complex, the inference can only be done approximately and the standard algorithms had to be adapted. In addition, different methods to train the model have been developed. Using this approach the alignment quality could be improved by up to 23 percent for 3 different language pairs compared to a combination of both IBM4-alignments. Furthermore the word alignment was used to generate new phrase tables. These could improve the translation quality significantly.