An exact dual decomposition algorithm for shallow semantic parsing with constraints

Authors:
Dipanjan Das;André F. T. Martins;Noah A. Smith
Affiliations:
Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA;Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA and Instituto de Telecomunicações, Instituto Superior Técnico, Lisboa, Portugal;Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA
Venue:
SemEval '12 Proceedings of the First Joint Conference on Lexical and Computational Semantics - Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation
Year:
2012

Citing 21
Cited 1

Automatic labeling of semantic roles

Computational Linguistics
Online large-margin training of dependency parsers

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Joint learning improves semantic role labeling

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Semantic role labeling via integer linear programming inference

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Semantic role labeling: an introduction to the special issue

Computational Linguistics
The importance of syntactic parsing and inference in semantic role labeling

Computational Linguistics
Dependency parsing by belief propagation

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
SemEval'07 task 19: frame semantic structure extraction

SemEval '07 Proceedings of the 4th International Workshop on Semantic Evaluations
LTH: semantic structure extraction using nonprojective dependency trees

SemEval '07 Proceedings of the 4th International Workshop on Semantic Evaluations
Probabilistic frame-semantic parsing

HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Beyond NomBank: a study of implicit arguments for nominal predicates

ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
SEMAFOR: Frame argument resolution with log-linear models

SemEval '10 Proceedings of the 5th International Workshop on Semantic Evaluation
On dual decomposition and linear programming relaxations for natural language processing

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Turbo parsers: dependency parsing by approximate variational inference

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Dual decomposition for parsing with non-projective head automata

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Exact decoding of syntactic translation models through Lagrangian relaxation

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Model-based aligner combination using dual decomposition

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
A comparison of loopy belief propagation and dual decomposition for integrated CCG supertagging and parsing

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Semi-supervised frame-semantic parsing for unknown predicates

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Exact decoding of phrase-based translation models through Lagrangian relaxation

EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Dual decomposition with many overlapping components

EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing

A tutorial on dual decomposition and lagrangian relaxation for inference in natural language processing

Journal of Artificial Intelligence Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a novel technique for jointly predicting semantic arguments for lexical predicates. The task is to find the best matching between semantic roles and sentential spans, subject to structural constraints that come from expert linguistic knowledge (e.g., in the FrameNet lexicon). We formulate this task as an integer linear program (ILP); instead of using an off-the-shelf tool to solve the ILP, we employ a dual decomposition algorithm, which we adapt for exact decoding via a branch-and-bound technique. Compared to a baseline that makes local predictions, we achieve better argument identification scores and avoid all structural violations. Runtime is nine times faster than a proprietary ILP solver.