ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Large-Margin Training of Dependency Parsers Using Pegasos Algorithm
Cited 7 time in scopus Download 0 time Share share facebook twitter linkedin kakaostory
저자
이창기, 임수종, 장명길
발행일
201006
출처
ETRI Journal, v.32 no.3, pp.486-489
ISSN
1225-6463
출판사
한국전자통신연구원 (ETRI)
DOI
https://dx.doi.org/10.4218/etrij.10.0209.0483
협약과제
09MS3100, 웹 QA 기술개발, 장명길
초록
This letter presents a modified Pegasos algorithm for graphbased dependency parsing. We show that the modified Pegasos algorithm outperforms the margin infused relaxed and passive aggressive algorithms in three languages.
키워드
Dependency parsing, Pegasos, Stochastic gradient descent
KSP 제안 키워드
Dependency Parsing, Dependency parser, Stochastic Gradient Descent