Dual decomposition for parsing with nonprojective head automata

Dual decomposition for parsing with nonprojective head automata (2010)

Cached

Download Links

by Terry Koo , Alexander M. Rush , Michael Collins , Tommi Jaakkola , David Sontag

Venue:	In Proc. of EMNLP
Citations:	31 - 6 self

BibTeX

@INPROCEEDINGS{Koo10dualdecomposition,
    author = {Terry Koo and Alexander M. Rush and Michael Collins and Tommi Jaakkola and David Sontag},
    title = {Dual decomposition for parsing with nonprojective head automata},
    booktitle = {In Proc. of EMNLP},
    year = {2010}
}

Bookmark

OpenURL

Abstract

This paper introduces algorithms for nonprojective parsing based on dual decomposition. We focus on parsing algorithms for nonprojective 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. 1

Citations

549	Tree-adjoining grammars - Joshi, Schabes - 1997
396	The syntactic process - Steedman - 2000
315	BMaximum-margin Markov networks - Taskar, Guestrin, et al. - 2003
177	2005b. Non-projective dependency parsing using spanning tree algorithms - McDonald, Pereira, et al.
123	Combinatorial optimization. Theory and algorithms - Korte, Vygen - 2008
111	2006. Online learning of approximate dependency parsing algorithms - McDonald, Pereira
47	Dependency parsing by belief propagation - Smith, Eisner - 2008
44	BTraining structural SVMs when exact inference is intractable - Finley, Joachims - 2008
40	Head Automata and Bilingual Tiling: Translation with Minimal Representations - Alshawi - 1996
38	Tightening LP relaxations for MAP using message passing - Sontag, Meltzer, et al. - 2008
37	Experiments with a higher-order projective dependency parser - Carreras - 2007
36	Integrating graphbased and transition-based dependency parsers - Nivre, McDonald - 2008
31	Structured learning with approximate inference - Kulesza, Pereira - 2008
30	Incremental integer linear programming for non-projective dependency parsing - Riedel, Clarke - 2006
27	Stacking dependency parsers - Martins, Das, et al. - 2008
25	Using Combinatorial Optimization within Max-Product Belief Propagation - Duchi, Tarlow, et al. - 2006
25	Concise Integer Linear Programming Formulations for Dependency Parsing - Martins, Smith, et al. - 2009
22	On the complexity of non-projective data-driven dependency parsing - McDonald, Satta - 2007
21	Structured prediction models via the matrix-tree theorem - Koo, Globerson, et al. - 2007
21	On dual decomposition and linear programming relaxations for natural language processing - Rush, Sontag, et al. - 2010
19	Probabilistic models of nonprojective dependency trees - Smith, Smith - 2007
10	Approximate primal solutions and rate analysis for dual subgradient methods - Nedić, Ozdaglar - 2009
8	Learning efficiently with approximate inference via dual losses - Meshi, Sontag, et al. - 2010