인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
DBpia AI
AI 에이전트
AI 아이디어
AI 리더
AI 뷰어
Citeasy
크롬 서지관리 다운로드
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
초록·키워드
This study proposes an ontology validation framework based on Competency Questions (CQs) and Large Language Models (LLMs) to automatically verify the semantic consistency of ontology elements. The proposed method defines the required classes and properties from CQs and evaluates their correspondence with existing ontologies through embedding-based similarity analysis. Using a small-scale Republic of Korea Navy ontology as a case study, three experiments were conducted to assess the effects of (1) providing Purpose and Scope information during CQ interpretation, (2) varying similarity thresholds, and (3) using different LLM models. Results show that including Purpose and Scope significantly improves validation accuracy, and a similarity threshold of 0.5 provides the most balanced performance. Among models, GPT-4.1 achieved the highest F1-score, while lightweight models demonstrated practical efficiency. These findings confirm that LLM-based CQ validation can reliably identify
semantic correspondence between CQs and ontology elements, even in structured defense domains. The proposed framework offers a foundation for developing intelligent ontology quality management systems applicable to large-scale military knowledge graphs.
semantic correspondence between CQs and ontology elements, even in structured defense domains. The proposed framework offers a foundation for developing intelligent ontology quality management systems applicable to large-scale military knowledge graphs.
본문·목차
인공지능 문자 인식 모델을 통해 추출된 텍스트로, 일부 오타나 오류가 포함될 수 있으나 지속적으로 개선 중입니다.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
최근 본 자료 전체보기
UCI(KEPA) : I410-151-26-02-094689437
