Handling Ambiguities of Bilingual Predicate-Argument Structures for Statistical Machine Translation

Feifei Zhai, Jiajun Zhang, Yu Zhou, Chengqing Zong

Abstract: Predicate-argument structure (PAS) has been demonstrated to be very effective in improving SMT performance. However, since a sourceside PAS might correspond to multiple different target-side PASs, there usually exist many PAS ambiguities during translation. In this paper, we group PAS ambiguities into two types: role ambiguity and gap ambiguity. Then we propose two novel methods to handle the two PAS ambiguities for SMT accordingly: 1) inside context integration; 2) a novel maximum entropy PAS disambiguation (MEPD) model. In this way, we incorporate rich context information of PAS for disambiguation. Then we integrate the two methods into a PASbased translation framework. Experiments show that our approach helps to achieve significant improvements on translation quality.