Paper: Word Alignment Via Quadratic Assignment

ACL ID N06-1015
Title Word Alignment Via Quadratic Assignment
Venue Human Language Technologies
Session Main Conference
Year 2006

Recently, discriminative word alignment methods have achieved state-of-the-art accuracies by extend- ing the range of information sources that can be easily incorporated into aligners. The chief advan- tage of a discriminative framework is the ability to score alignments based on arbitrary features of the matching word tokens, including orthographic form, predictions of other models, lexical context and so on. However, the proposed bipartite match- ing model of Taskar et al. (2005), despite being tractable and effective, has two important limita- tions. First, it is limited by the restriction that words have fertility of at most one. More impor- tantly, first order correlations between consecutive words cannot be directly captured by the model. In this work, we address these limitations by...