Improving Word Alignment Using Syntactic Dependencies

We introduce a word alignment framework that facilitates the incorporation of syntax en-coded 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 fo-cuses on aligning the remaining words relying on dependency information invoked by the ac-quired anchor links. We show that our syntax-enhanced word alignment approach leads to a 10.32 % and 5.57 % relative decrease in align-ment error rate compared to a generative word alignment model and a syntax-proof discrim-inative word alignment model respectively. Furthermore, our approach is evaluated ex-trinsically using a phrase-based statistical ma-chine translation system. The results show that SMT systems based on our word align-ment approach tend to generate shorter out-puts. Without length penalty, using our word alignments yields statistically significant im-provement in Chinese–English machine trans-lation in comparison with the baseline word alignment.