Hierarchical Search for Word Alignment

We present a simple yet powerful hierarchical 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 discriminative model incorporating hundreds of features, and trained on a relatively small amount of annotated data. We report results on Arabic-English word alignment and translation tasks. Our model outperforms a GIZA++ Model-4 baseline by

• Type: Journal
• Year: 2010
• Where: ACL
• Authors: Jason Riesa, Daniel Marcu
• Keywords: ACL 2010, Arabic-English Word Alignment, Automatic Word Alignment, Computational Linguistics, Word Alignment