Utilizing Target-Side Semantic Role Labels to Assist Hierarchical Phrase-based Machine Translation

摘要

In this paper we present a novel approach of utilizing Semantic Role Labeling (SRL) information to improve Hierarchical Phrase-based Machine Translation. We propose an algorithm to extract SRL-aware Synchronous Context-Free Grammar (SCFG) rules. Conventional Hiero-style SCFG rules will also be extracted in the same framework. Special conversion rules are applied to ensure that when SRL-aware SCFG rules are used in derivation, the decoder only generates hypotheses with complete semantic structures. We perform machine translation experiments using 9 different Chinese-English test-sets. Our approach achieved an average BLEU score improvement of 0.49 as well as 1.21 point reduction in TER.