Latent Domain Word Alignment for Heterogeneous Corpora

Cuong Hoang, Khalil Sima'an

Abstract: This work focuses on the insensitivity of existing word alignment models to domain differences, which often yields suboptimal results on large heterogeneous data. A novel latent domain word alignment model is proposed, which induces domain-conditioned lexical and alignment statistics. We propose to train the model on a heterogeneous corpus under partial supervision, using a small number of seed samples from different domains. The seed samples allow estimating sharper, domain-conditioned word alignment statistics for sentence pairs. Our experiments show that the derived domain-conditioned statistics, once combined together, produce notable improvements both in word alignment accuracy and in translation accuracy of their resulting SMT systems.