ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Open Domain Question Answering Using Wikipedia-Based Knowledge Model
Cited 39 time in scopus Download 0 time Share share facebook twitter linkedin kakaostory
저자
류법모, 장명길, 김현기
발행일
201409
출처
Information Processing & Management, v.50 no.5, pp.683-692
ISSN
0306-4573
출판사
Elsevier
DOI
https://dx.doi.org/10.1016/j.ipm.2014.04.007
협약과제
14MS4400, 휴먼 지식증강 서비스를 위한 지능진화형 Wise QA 플랫폼 기술 개발, 박상규
초록
This paper describes the use of Wikipedia as a rich knowledge source for a question answering (QA) system. We suggest multiple answer matching modules based on different types of semi-structured knowledge sources of Wikipedia, including article content, infoboxes, article structure, category structure, and definitions. These semi-structured knowledge sources each have their unique strengths in finding answers for specific question types, such as infoboxes for factoid questions, category structure for list questions, and definitions for descriptive questions. The answers extracted from multiple modules are merged using an answer merging strategy that reflects the specialized nature of the answer matching modules. Through an experiment, our system showed promising results, with a precision of 87.1%, a recall of 52.7%, and an F-measure of 65.6%, all of which are much higher than the results of a simple text analysis based system. © 2014 Elsevier Ltd. All rights reserved.
키워드
Question-answering, Semi-structured knowledge, Wikipedia
KSP 제안 키워드
F-measure, Merging strategy, Open domain, Semi-structured, Text analysis, Wikipedia-based, based system, knowledge model, knowledge sources, multiple modules, question answering