Dual decomposition for parsing with non-projective head automata

• Main Authors: Koo, Terry (Contributor), Rush, Alexander Matthew (Contributor), Collins, Michael (Contributor), Jaakkola, Tommi S. (Contributor), Sontag, David Alexander (Contributor)
• Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
• Format: Article
• Language: English
• Published: Association for Computational Linguistics, 2011-11-22T14:20:51Z.
• Subjects: Article
• Online Access: Get fulltext

 This paper introduces algorithms for non-projective parsing based on dual decomposition. We focus on parsing algorithms for non-projective head automata, a generalization of head-automata models to non-projective structures. The dual decomposition algorithms are simple and efficient, relying on standard dynamic programming and minimum spanning tree algorithms. They provably solve an LP relaxation of the non-projective parsing problem. Empirically the LP relaxation is very often tight: for many languages, exact solutions are achieved on over 98% of test sentences. The accuracy of our models is higher than previous work on a broad range of datasets.