A robust combination strategy for semantic role labeling

A robust combination strategy for semantic role labeling (2005)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Lluís Màrquez , Mihai Surdeanu , Pere Comas , Jordi Turmo

Venue:	Journal of Artificial Intelligence Research
Citations:	25 - 7 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	A robust combination strategy for semantic role labeling	INFERENCE
AUTHOR NAME	Lluís Màrquez	SVM HeaderParse 0.2
AUTHOR AFFIL	Technical University of Catalunya	SVM HeaderParse 0.2
AUTHOR ADDR	Barcelona, Spain	SVM HeaderParse 0.2
AUTHOR NAME	Mihai Surdeanu	SVM HeaderParse 0.2
AUTHOR AFFIL	Technical University of Catalunya	SVM HeaderParse 0.2
AUTHOR ADDR	Barcelona, Spain	SVM HeaderParse 0.2
AUTHOR NAME	Pere Comas	SVM HeaderParse 0.2
AUTHOR AFFIL	Technical University of Catalunya	SVM HeaderParse 0.2
AUTHOR ADDR	Barcelona, Spain	SVM HeaderParse 0.2
AUTHOR NAME	Jordi Turmo	SVM HeaderParse 0.2
AUTHOR AFFIL	Technical University of Catalunya	SVM HeaderParse 0.2
AUTHOR ADDR	Barcelona, Spain	SVM HeaderParse 0.2
ABSTRACT	This paper focuses on semantic role labeling using automatically-generated syntactic information. A simple and robust strategy for system combination is presented, which allows to partially recover from input parsing errors and to significantly boost results of individual systems. This combination scheme is also very flexible since the individual systems are not required to provide any information other than their solution. Extensive experimental evaluation in the CoNLL-2005 shared task framework supports our previous claims. The proposed architecture outperforms the best results reported in that evaluation exercise.	SVM HeaderParse 0.2
YEAR	2005	INFERENCE
VENUE	Journal of Artificial Intelligence Research	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	105--151	INFERENCE
VOLUME	29	INFERENCE
CITATIONS	15 found	ParsCit 1.0