Paper: Optimizing Word Alignment Combination For Phrase Table Training

ACL ID P09-2058
Title Optimizing Word Alignment Combination For Phrase Table Training
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2009
Authors

Combining word alignments trained in two translation directions has mostly re- lied on heuristics that are not directly motivated by intended applications. We propose a novel method that performs combination as an optimization process. Our algorithm explicitly maximizes the ef- fectiveness function with greedy search for phrase table training or synchronized grammar extraction. Experimental results show that the proposed method leads to significantly better translation quality than existing methods. Analysis suggests that this simple approach is able to maintain accuracy while maximizing coverage.