Paper: Unsupervised Word Alignment Using Frequency Constraint in Posterior Regularized EM

ACL ID D14-1017
Title Unsupervised Word Alignment Using Frequency Constraint in Posterior Regularized EM
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014
Authors

Generative word alignment models, such as IBM Models, are restricted to one- to-many alignment, and cannot explicitly represent many-to-many relationships in a bilingual text. The problem is par- tially solved either by introducing heuris- tics or by agreement constraints such that two directional word alignments agree with each other. In this paper, we fo- cus on the posterior regularization frame- work (Ganchev et al., 2010) that can force two directional word alignment models to agree with each other during train- ing, and propose new constraints that can take into account the difference between function words and content words. Ex- perimental results on French-to-English and Japanese-to-English alignment tasks show statistically significant gains over the previous posterior regularizat...