ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Graph-Based Knowledge Consolidation in Ontology Population
Cited 1 time in scopus Download 2 time Share share facebook twitter linkedin kakaostory
저자
류법모, 장명길, 김현기, 박소영
발행일
201309
출처
IEICE Transactions on Information and Systems, v.E96.D no.9, pp.2139-2142
ISSN
0916-8532
출판사
일본, 전자정보통신학회 (IEICE)
DOI
https://dx.doi.org/10.1587/transinf.E96.D.2139
협약과제
13VS2500, 휴먼 지식증강 서비스를 위한 지능진화형 Wise QA 플랫폼 기술 개발, 박상규
초록
We propose a novel method for knowledge consolidation based on a knowledge graph as a next step in relation extraction from text. The knowledge consolidation method consists of entity consolidation and relation consolidation. During the entity consolidation process, identical entities are found and merged using both name similarity and relation similarity measures. In the relation consolidation process, incorrect relations are removed using cardinality properties, temporal information and relation weight in given graph structure. In our experiment, we could generate compact and clean knowledge graphs where number of entities and relations are reduced by 6.1% and by 17.4% respectively with increasing relation accuracy from 77.0% to 85.5%. Copyright © 2013 The Institute of Electronics, Information and Communication Engineers.
키워드
Entity consolidation, Knowledge consolidation, Knowledge graph, Relation consolidation
KSP 제안 키워드
Consolidation process, Graph structure, Graph-based, Information and communication, Ontology Population, Relation extraction, knowledge graph, novel method, similarity measure, temporal information