Learning Tractable Word Alignment Models with Complex Constraints

Loading...
Thumbnail Image
Penn collection
Lab Papers (GRASP)
Degree type
Discipline
Subject
Engineering
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Contributor
Abstract

Word-level alignment of bilingual text is a critical resource for a growing variety of tasks. Probabilistic models for word alignment present a fundamental trade-off between richness of captured constraints and correlations versus efficiency and tractability of inference. In this article, we use the Posterior Regularization framework (Graça, Ganchev, and Taskar 2007) to incorporate complex constraints into probabilistic models during learning without changing the efficiency of the underlying model. We focus on the simple and tractable hidden Markov model, and present an efficient learning algorithm for incorporating approximate bijectivity and symmetry constraints. Models estimated with these constraints produce a significant boost in performance as measured by both precision and recall of manually annotated alignments for six language pairs. We also report experiments on two different tasks where word alignments are required: phrase-based machine translation and syntax transfer, and show promising improvements over standard methods.

Advisor
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Publication date
2010-03-10
Journal title
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Suggested Citation: J. Graça, K. Ganchev and B. Taskar. (2010). "Learning TractableWord AlignmentModels with Complex Constraints." Computational Linguistics. Vol. 36(3). p. 481-504. © 2010 MIT Press http://www.mitpressjournals.org/loi/coli
Recommended citation
Collection