Generalized inference with multiple semantic role labeling systems

Generalized inference with multiple semantic role labeling systems (2005)

Cached

Download Links

by Peter Koomen , Vasin Punyakanok , Dan Roth , Wen-tau Yih

Venue:	In Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005
Citations:	27 - 3 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Generalized inference with multiple semantic role labeling systems	INFERENCE
AUTHOR NAME	Peter Koomen	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; University of Illinois at Urbana-Champaign	SVM HeaderParse 0.2
AUTHOR ADDR	Urbana, IL 61801, USA	SVM HeaderParse 0.2
AUTHOR NAME	Vasin Punyakanok	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; University of Illinois at Urbana-Champaign	SVM HeaderParse 0.2
AUTHOR ADDR	Urbana, IL 61801, USA	SVM HeaderParse 0.2
AUTHOR NAME	Dan Roth	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; University of Illinois at Urbana-Champaign	SVM HeaderParse 0.2
AUTHOR ADDR	Urbana, IL 61801, USA	SVM HeaderParse 0.2
AUTHOR NAME	Wen-tau Yih	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; University of Illinois at Urbana-Champaign	SVM HeaderParse 0.2
AUTHOR ADDR	Urbana, IL 61801, USA	SVM HeaderParse 0.2
ABSTRACT	We present an approach to semantic role labeling (SRL) that takes the output of multiple argument classifiers and combines them into a coherent predicateargument output by solving an optimization problem. The optimization stage, which is solved via integer linear programming, takes into account both the recommendation of the classifiers and a set of problem specific constraints, and is thus used both to clean the classification results and to ensure structural integrity of the final role labeling. We illustrate a significant improvement in overall SRL performance	SVM HeaderParse 0.2
YEAR	2005	INFERENCE
VENUE	In Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	181--184	INFERENCE
CITATIONS	9 found	ParsCit 1.0