Efficient latent structural perceptron with hybrid trees for semantic parsing

Authors:
Junsheng Zhou;Juhong Xu;Weiguang Qu
Affiliations:
School of Computer Science and Technology, Nanjing Normal University, China and Jiangsu Research Center of Information Security & Privacy Technology, China;School of Computer Science and Technology, Nanjing Normal University, China and Jiangsu Research Center of Information Security & Privacy Technology, China;School of Computer Science and Technology, Nanjing Normal University, China and Jiangsu Research Center of Information Security & Privacy Technology, China and State Key Lab. for Novel Softwar ...
Venue:
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Year:
2013

Citing 16
Cited 0

Simple fast algorithms for the editing distance between trees and related problems

SIAM Journal on Computing
Parallel Optimization: Theory, Algorithms and Applications

Parallel Optimization: Theory, Algorithms and Applications
Document Ranking and the Vector-Space Model

IEEE Software
Discriminative training methods for hidden Markov models: theory and experiments with perceptron algorithms

EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
Using string-kernels for learning semantic parsers

ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Learning for semantic parsing with statistical machine translation

HLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
Discriminative learning and spanning tree algorithms for dependency parsing

Discriminative learning and spanning tree algorithms for dependency parsing
Discriminative reranking for semantic parsing

COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
Learning for semantic parsing and natural language generation using statistical machine translation techniques

Learning for semantic parsing and natural language generation using statistical machine translation techniques
A generative model for parsing natural language to meaning representations

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Learning to transform natural to formal languages

AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 3
Latent variable perceptron algorithm for structured classification

IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Learning a compositional semantic parser using an existing syntactic parser

ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2
A statistical semantic parser that integrates syntax and semantics

CONLL '05 Proceedings of the Ninth Conference on Computational Natural Language Learning
Inducing probabilistic CCG grammars from logical form with higher-order unification

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Semantic parsing with Bayesian tree transducers

ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

Discriminative structured prediction models have been widely used in many natural language processing tasks, but it is challenging to apply the method to semantic parsing. In this paper, by introducing hybrid tree as a latent structure variable to close the gap between the input sentences and output representations, we formulate semantic parsing as a structured prediction problem, based on the latent variable perceptron model incorporated with a tree edit-distance loss as optimization criterion. The proposed approach maintains the advantage of a discriminative model in accommodating flexible combination of features and naturally incorporates an efficient decoding algorithm in learning and inference. Furthermore, in order to enhance the efficiency and accuracy of inference, we design an effective approach based on vector space model to extract a smaller subset of relevant MR productions for test examples. Experimental results on publicly available corpus show that our approach significantly outperforms previous systems.