용어 간의 다양한 관계 추출에 의한 온톨로지의 자동 생성 방법에 관한 연구

• 발행기관: 한국산업경영시스템학회
• 저자명: 김영태 이동주 김치수
• 간행물 정보: 『한국산업경영시스템학회 학술대회』2019년 추계학술대회 논문집, 171~171쪽, 전체 1쪽
• 주제분류: 공학 > 산업공학
• 파일형태: PDF
• 발행일자: 2019.10.30

영문 초록

This paper proposes a method to automatically creating ontology by extracting various relationships between the terms needed for establishing the ontology of a specific domain. To extract the relationship between the terms, there is proposed a method of reducing the size of a searching space by taking a matching set of patterns into account and connecting a join-set concept and a pattern array. The extracted relationships are created into the ontology by encoding the structure of the ontology with a set of axioms. For an efficient solution, a search space for the set is expressed in an integer programming problem, and a matrix is decreased by using a simple reduction of removing rules useless to find an optimal solution. In result, this paper provides a method of generalizing a pattern from given data, and reducing a search space while retaining a potentially useful pattern, and proposes and valuates a method of efficiently and automat ically creating ontology by an algorithm of establishing an extracted binary relationship into structuralized ontology.

목차

요약

서론

관련 연구

온톨로지 자동 생성

실험 및 평가

결론

참고문헌