Paper: Hierarchical Search for Word Alignment

ACL ID P10-1017
Title Hierarchical Search for Word Alignment
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2010
Authors

We present a simple yet powerful hier- archical search algorithm for automatic word alignment. Our algorithm induces a forest of alignments from which we can efficiently extract a ranked k-best list. We score a given alignment within the forest with a flexible, linear discrimina- tive model incorporating hundreds of fea- tures, and trained on a relatively small amount of annotated data. We report re- sults on Arabic-English word alignment and translation tasks. Our model out- performs a GIZA++ Model-4 baseline by 6.3 points in F-measure, yielding a 1.1 BLEU score increase over a state-of-the-art syntax-based machine translation system.