Title
Dependency-based semantic role labeling using sequence labeling with a structural SVM
Abstract
Semantic Role Labeling (SRL) systems aim at determining the semantic role labels of the arguments of the predicates in natural language text. SRL systems can usually be built to work upon the result of constitient analysis (constituent-based), or dependency parsing (dependency-based). SRL systems can use either classification or sequence labeling as the main processing mechanism. In this paper, we show that a dependency-based SRL system using sequence labeling can achieve state-of-the-art performance when a new structural SVM adapted from the Pegasos algorithm is exploited for performing sequence labeling.
Year
DOI
Venue
2013
10.1016/j.patrec.2013.01.022
Pattern Recognition Letters
Keywords
Field
DocType
dependency-based semantic role,new structural svm,dependency parsing,semantic role,dependency-based srl system,constitient analysis,semantic role label,natural language text,srl system,pegasos algorithm,main processing mechanism,semantic role labeling,natural language,sequence labeling
Sequence labeling,Pattern recognition,Computer science,Support vector machine,Dependency grammar,Natural language,Artificial intelligence,Natural language processing,Predicate (grammar),Semantic role labeling
Journal
Volume
Issue
ISSN
34
6
0167-8655
Citations 
PageRank 
References 
2
0.36
32
Authors
3
Name
Order
Citations
PageRank
Soojong Lim1362.80
Changki Lee227926.18
Dong-yul Ra3355.47