acl acl2010 acl2010-163 acl2010-163-reference knowledge-graph by maker-knowledge-mining

163 acl-2010-Learning Lexicalized Reordering Models from Reordering Graphs


Source: pdf

Author: Jinsong Su ; Yang Liu ; Yajuan Lv ; Haitao Mi ; Qun Liu

Abstract: 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. 1


reference text