BROWSE
Detail
Journal Article
Dependency-Based Semantic Role Labeling Using Sequence Labeling with a Structural SVM
Cited 11 time in 
Share 
Share
- Authors
- Soojong Lim, Changki Lee, Dongyul Ra
- Issue Date
- 2013-04
- Citation
- Pattern Recognition Letters, v.34, no.6, pp.696-702
- ISSN
- 0167-8655
- Publisher
- Elsevier
- Language
- English
- Type
- Journal Article
- 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. © 2013 Elsevier B.V. All rights reserved.
- KSP Keywords
- Art performance, Dependency Parsing, Processing mechanism, Sequence Labeling, Structural SVM(SSVM), natural language, semantic role labeling, state-of-The-Art