A Framework for Effectively Integrating Hard and Soft Syntactic Rules into Phrase Based Translation

In adding syntactic knowledge into phrase-based translation, using hard or soft syntactic rules to reorder the source-language aiming to closely approximate the targetlanguage word order has been successful in improving translation quality. However, it suffers from propagating the pre-reordering errors to the later translation step (decoding). In this paper, we propose a novel framework to integrate hard and soft syntactic rules into phrase-based translation more effectively. For a source sentence to be translated, hard or soft syntactic rules are first acquired from the source parse tree prior to translation, and then instead of reordering the source sentence directly, the rules are used as a strong feature integrated into our elaborately designed model to help phrase reordering in the decoding stage. The experiments on NIST Chinese-to-English translation show that our approach, whether incorporating hard or soft rules, significantly outperforms the previous methods.