Dual decomposition for parsing with non-projective head automata
Author(s)Koo, Terry; Rush, Alexander Matthew; Collins, Michael; Jaakkola, Tommi S.; Sontag, David Alexander
MetadataShow full item record
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.
DepartmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Association for Computational Linguistics
Terry Koo, Alexander M. Rush, Michael Collins, Tommi Jaakkola, and David Sontag. 2010. Dual decomposition for parsing with non-projective head automata. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing (EMNLP '10). Association for Computational Linguistics, Stroudsburg, PA, USA, 1288-1298.
Author's final manuscript