Departmental Papers (CIS)

Date of this Version

2006

Document Type

Conference Paper

Comments

Simon Lacoste-Julien, Ben Taskar, Dan Klein, and Michael I. Jordan. 2006. Word alignment via quadratic assignment. In Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT-NAACL '06). Association for Computational Linguistics, Stroudsburg, PA, USA, 112-119. DOI=10.3115/1220835.1220850 http://dx.doi.org/10.3115/1220835.1220850

© ACM, 2006. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, {(2006)} http://doi.acm.org/10.3115/1220835.1220850" Email permissions@acm.org

Abstract

Recently, discriminative word alignment methods have achieved state-of-the-art accuracies by extending the range of information sources that can be easily incorporated into aligners. The chief advantage 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 matching model of Taskar et al. (2005), despite being tractable and effective, has two important limitations. First, it is limited by the restriction that words have fertility of at most one. More importantly, first order correlations between consecutive words cannot be directly captured by the model. In this work, we address these limitations by enriching the model form. We give estimation and inference algorithms for these enhancements. Our best model achieves a relative AER reduction of 25% over the basic matching formulation, outperforming intersected IBM Model 4 without using any overly compute-intensive features. By including predictions of other models as features, we achieve AER of 3:8 on the standard Hansards dataset.

Share

COinS
 

Date Posted: 16 July 2012