Paper Type

ERF

Abstract

Information retrieval systems use ontologies to assist with document processing, but developing ontologies is knowledge-intensive and require detailed analysis of domain-specific knowledge. This paper addresses the limitations in ontology development research. It introduces a novel LLM based method called CESR-OL for automated concept extraction task to improve accuracy and domain relevance. A design science approach is adopted for this study. Evaluation will compare CESR-OL's performance against traditional machine learning methods. The study anticipates that CESR-OL will outperform existing methods, demonstrating the potential of LLMs for concept extraction in ontology learning and enabling more automated, accurate, and contextually aware ontologies.

Paper Number

2341

Author Connect URL

https://authorconnect.aisnet.org/conferences/AMCIS2025/papers/2341

Comments

SIGODIS

Author Connect Link

Share

COinS
 
Aug 15th, 12:00 AM

Large Language Model Enhanced Concept Extraction Method for Ontology Learning

Information retrieval systems use ontologies to assist with document processing, but developing ontologies is knowledge-intensive and require detailed analysis of domain-specific knowledge. This paper addresses the limitations in ontology development research. It introduces a novel LLM based method called CESR-OL for automated concept extraction task to improve accuracy and domain relevance. A design science approach is adopted for this study. Evaluation will compare CESR-OL's performance against traditional machine learning methods. The study anticipates that CESR-OL will outperform existing methods, demonstrating the potential of LLMs for concept extraction in ontology learning and enabling more automated, accurate, and contextually aware ontologies.

When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.