Two-Neighbor Orientation Model with Cross-Boundary Global Contexts
Hendra Setiawan, Bowen Zhou, Bing Xiang and Libin Shen
The 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013)
Sofia, Bulgaria, August 4-9, 2013
Long distance reordering remains one of the greatest challenges in Statistical Machine Translation research as it involves contextual information that may go beyond the confine of translation units. In this paper, we propose Two-Neighbor Orientation model that jointly models orientation decisions between anchors and two neighboring multi unit chunks that cross phrase or rule boundaries. We explicitly model the longest span of such chunks, referred to as Maximal Orientation Span, to introduce global parameter that can guide underlying local decisions. We integrate our proposed model into a state-of-the-art string-to-dependency translation system and demonstrate the efficacy of our proposal in a large-scale Chinese-to-English translation task. On NIST MT08 set, our most advanced model brings around +2.0 BLEU and
-1.0 TER improvement.
Conference Manager (V2.61.0 - Rev. 2792M)