Dependency forest based word alignment

Abstract

A hierarchical word alignment model that searches for k-best partial alignments on target constituent 1-best parse trees has been shown to outperform previous models. However, relying solely on 1-best parses trees might hinder the search for good alignments because 1-best trees are not necessarily the best for word alignment tasks in practice. This paper introduces a dependency forest based word alignment model, which utilizes target dependency forests in an attempt to minimize the impact on limitations attributable to 1-best parse trees. We present how k-best alignments are constructed over target-side dependency forests. Alignment experiments on the Japanese-English language pair show a relative error reduction of 4% of the alignment score compared to a model with 1-best parse trees.