Learning Lexicalized Reordering Models from Reordering Graphs

Lexicalized reordering models play a crucial role in phrase-based translation systems. They are usually learned from the word-aligned bilingual corpus by examining the reordering relations of adjacent phrases. Instead of just checking whether there is one phrase adjacent to a given phrase, we argue that it is important to take the number of adjacent phrases into account for better estimations of reordering models. We propose to use a structure named reordering graph, which represents all phrase segmentations of a sentence pair, to learn lexicalized reordering models efficiently. Experimental results on the NIST Chinese-English test sets show that our approach significantly outperforms the baseline method.

• Type: Journal
• Year: 2010
• Where: ACL
• Authors: Jinsong Su, Yang Liu, Yajuan Lü, Haitao Mi, Qun Liu
• Keywords: ACL 2010, Adjacent Phrases, Computational Linguistics, Phrase-based Translation Systems, Word-aligned Bilingual Corpus