This paper reports an effort to construct a grand-scale Korean thesaurus that can be used for enhancing retrieval performance in various fields. This thesaurus is currently being used for indexing and retrieving purpose and new terms are being added to it. As the new demands on retrieval performance increase in Korea, developing a grand-scale ontology appears to be necessary so a project is undertaken to transfer the current thesaurus into an ontology system. The paper describes how the thesaurus is constructed and prepared to be the base for an ontology system.
심사자 자동추천시스템은 심사 대상에 대한 포괄성, 전문성, 공정성, 타당성을 확보할 수 있도록 설계되어야 한다. 이를 위해 본 연구는 다면적인 학문분야분류표의 각 범주 간 연관성을 자동으로 산출할 수 있는 확률적 온톨로지를 적용하여 포괄적으로 심사자 추천 범위를 넓히고 전문성을 반영한 심사자 랭킹을 가능하도록 한다. 또한 연구자 간의 멘터, 공저역, 공동연구를 포함하는 연구자 네트워크를 구축하고 이를 심사자 배제 규칙으로 활용함으로써 공정한 심사자 추천이 이루어질 수 있도록 한다. 아울러, 전문가들을 통해 상기 방법론과 패널 결과를 검증 받아 타당성 있는 시스템이 갖추어야 할 방향을 제시한다.
Automatic Recommendation System of Panel pool should be designed to support universal, expertness, fairness, and reasonableness in the process of review of proposals. In this research, we apply the theory of probabilistic ontology to measure relatedness between terms in the classification of academic domain, enlarge the number of review candidates , and rank recommendable reviewers according to their expertness. In addition, we construct a researcher network connecting among researchers according to their various relationships like mentor, coauthor, and cooperative research. We use the researcher network to exclude inappropriate reviewers and support fairness of reviewer recommendation process. Our methodology recommending proper reviewers is verified from experts in the field of proposal examination. It propose the proper method for developing a resonable reviewer recommendation system.