상세정보
학술지
Dependency-Based Semantic Role Labeling Using Sequence Labeling with a Structural SVM
- 저자
- 임수종, 이창기, 나동렬
- 발행일
- 201304
- 출처
- Pattern Recognition Letters, v.34 no.6, pp.696-702
- ISSN
- 0167-8655
- 출판사
- Elsevier
- 협약과제
- 13VS1200, 웹 인텔리전스를 위한 웹 폭증 데이터 분석형 리스닝 플랫폼용 소셜웹 이슈 탐지-모니터링 및 예측 원천 기술 개발, 김현기
- 초록
- 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 제안 키워드
- Art performance, Dependency Parsing, Processing mechanism, Sequence Labeling, Structural SVM(SSVM), natural language, semantic role labeling, state-of-The-Art