Paper: Distortion Models For Statistical Machine Translation

ACL ID P06-1067
Title Distortion Models For Statistical Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2006

In this paper, we argue that n-gram lan- guage models are not sufficient to address word reordering required for Machine Trans- lation. We propose a new distortion model that can be used with existing phrase-based SMT decoders to address those n-gram lan- guage model limitations. We present empirical results in Arabic to English Machine Transla- tion that show statistically significant improve- ments when our proposed model is used. We also propose a novel metric to measure word order similarity (or difference) between any pair of languages based on word alignments.