Multi-task Learning for Word Alignment and Dependency Parsing

Word alignment and parsing are two important components for syntax based machine translation. The inconsistent models for alignment and parsing caused problems during translation pair extraction. In this paper, we do word alignment and dependency parsing in a multi-task learning framework, in which word alignment and dependency parsing are consistent and assisted with each other. Our experiments show significant improvement not only for both word alignment and dependency parsing, but also the final translation performance.