NeurAlign: combining word alignments using neural networks

This paper presents a novel approach to combining different word alignments. We view word alignment as a pattern classification problem, where alignment combination is treated as a classifier ensemble, and alignment links are adorned with linguistic features. A neural network model is used to learn word alignments from the individual alignment systems. We show that our alignment combination approach yields a significant 20--34% relative error reduction over the best-known alignment combination technique on English-Spanish and English-Chinese data.