Improving word alignment using syntactic dependencies

Abstract

We introduce a word alignment framework that facilitates the incorporation of syntax encoded in bilingual dependency tree pairs. Our model consists of two sub-models: an anchor word alignment model which aims to find a set of high-precision anchor links and a syntax-enhanced word alignment model which focuses on aligning the remaining words relying on dependency information invoked by the acquired anchor links. We show that our syntax-enhanced word alignment approach leads to a 10.32% and 5.57% relative decrease in alignment error rate compared to a generative word alignment model and a syntax-proof discriminative word alignment model respectively. Furthermore, our approach is evaluated extrinsically using a phrase-based statistical machine translation system. The results show that SMT systems based on our word alignment approach tend to generate shorter outputs. Without length penalty, using our word alignments yields statistically significant improvement in Chinese-English machine translation in comparison with the baseline word alignment.