|
|
|
|
LEADER |
01967 am a22003013u 4500 |
001 |
67290 |
042 |
|
|
|a dc
|
100 |
1 |
0 |
|a Koo, Terry
|e author
|
100 |
1 |
0 |
|a Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
|e contributor
|
100 |
1 |
0 |
|a Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
|e contributor
|
100 |
1 |
0 |
|a Jaakkola, Tommi S.
|e contributor
|
100 |
1 |
0 |
|a Koo, Terry
|e contributor
|
100 |
1 |
0 |
|a Rush, Alexander Matthew
|e contributor
|
100 |
1 |
0 |
|a Collins, Michael
|e contributor
|
100 |
1 |
0 |
|a Jaakkola, Tommi S.
|e contributor
|
100 |
1 |
0 |
|a Sontag, David Alexander
|e contributor
|
700 |
1 |
0 |
|a Rush, Alexander Matthew
|e author
|
700 |
1 |
0 |
|a Collins, Michael
|e author
|
700 |
1 |
0 |
|a Jaakkola, Tommi S.
|e author
|
700 |
1 |
0 |
|a Sontag, David Alexander
|e author
|
245 |
0 |
0 |
|a Dual decomposition for parsing with non-projective head automata
|
260 |
|
|
|b Association for Computational Linguistics,
|c 2011-11-22T14:20:51Z.
|
856 |
|
|
|z Get fulltext
|u http://hdl.handle.net/1721.1/67290
|
520 |
|
|
|a 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.
|
520 |
|
|
|a United States. Defense Advanced Research Projects Agency (contract FA8750-09-C-0181)
|
546 |
|
|
|a en_US
|
655 |
7 |
|
|a Article
|
773 |
|
|
|t Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
|