An LLM supported approach to ontology and knowledge graph construction

作者：Hang Yang, Liang Xiao, Rujun Zhu, Ziji Liu, Jianxia Chen · 年份：2024 · DOI：10.1109/bibm62325.2024.10822222 · 被引用次数：12 · 研究领域：Semantic Web and Ontologies、Service-Oriented Architecture and Web Services、Cognitive Computing and Networks

The continuous development in the medical field faces multiple challenges in managing a large amount of literature and research results using traditional ontology and knowledge graph construction methods. These challenges include high labor costs, limited coverage, and poor dynamism of traditional ontology and knowledge graph construction methods. Large language models (LLMs) can solve various natural language processing tasks and can understand and generate human-like natural language, which makes automated construction of ontology expansion and knowledge graphs (KGs) possible. This paper proposes an ontology expansion method based on LLMs, using LLMs to formulate competency questions (CQs) to extend the initial ontology, and then constructing the knowledge graph based on the extended ontology. We demonstrated the feasibility of the method by creating a knowledge graph for breast cancer treatment. The combination of LLMs-based medical ontology and knowledge graph can achieve more efficient medical knowledge management and application, promoting the informatization and intelligent development of the medical field.