Towards Ontology Construction with Language Models

TL;DR

This paper proposes a method that leverages large language models like GPT 3.5 to automatically build concept hierarchies within specific domains, demonstrating their usefulness in ontology construction.

Contribution

The paper introduces a novel approach utilizing LLMs for automated ontology construction, which has not been extensively explored before.

Findings

LLMs can effectively assist in constructing concept hierarchies.

The method is applicable across various domains.

Experimental results show promising accuracy in hierarchy generation.

Abstract

We present a method for automatically constructing a concept hierarchy for a given domain by querying a large language model. We apply this method to various domains using OpenAI's GPT 3.5. Our experiments indicate that LLMs can be of considerable help for constructing concept hierarchies.