Distortion Models for Statistical Machine Translation

In this paper, we argue that n-gram language models are not sufficient to address word reordering required for Machine Translation. We propose a new distortion model that can be used with existing phrase-based SMT decoders to address those n-gram language model limitations. We present empirical results in Arabic to English Machine Translation that show statistically significant improvements 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.

• Type: Conference
• Year: 2006
• Where: ACL
• Authors: Yaser Al-Onaizan, Kishore Papineni
• Keywords: ACL 2006, ACL 2007, Machine Translation, N-gram Language Model, Phrase-based Smt Decoders