Sentence compression with semantic role constraints

Authors:
Katsumasa Yoshikawa;Tsutomu Hirao;Ryu Iida;Manabu Okumura
Affiliations:
Tokyo Institute of Technology, Japan, and IBM Research-Tokyo, IBM Japan, Ltd.;NTT Corporation, Japan;Tokyo Institute of Technology, Japan;Tokyo Institute of Technology, Japan
Venue:
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers - Volume 2
Year:
2012

Citing 11
Cited 0

Summarization beyond sentence extraction: a probabilistic approach to sentence compression

Artificial Intelligence
Statistical sentence condensation using ambiguity packing and stochastic disambiguation methods for Lexical-Functional Grammar

NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Markov logic networks

Machine Learning
Non-projective dependency parsing using spanning tree algorithms

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Dependency-based syntactic-semantic analysis with PropBank and NomBank

CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning
Sentence compression beyond word deletion

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Global inference for sentence compression an integer linear programming approach

Journal of Artificial Intelligence Research
Sentence compression as tree transduction

Journal of Artificial Intelligence Research
An extractive supervised two-stage method for sentence compression

HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Semantic role features for machine translation

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Discourse constraints for document compression

Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

For sentence compression, we propose new semantic constraints to directly capture the relations between a predicate and its arguments, whereas the existing approaches have focused on relatively shallow linguistic properties, such as lexical and syntactic information. These constraints are based on semantic roles and superior to the constraints of syntactic dependencies. Our empirical evaluation on the Written News Compression Corpus (Clarke and Lapata, 2008) demonstrates that our system achieves results comparable to other state-of-the-art techniques.