Meronymic Ontology Extraction via Large Language Models

2025-10-11

AI Summary

To address the labor-intensive and non-scalable nature of manual product ontology construction, this paper proposes a fully automated method for extracting part-whole (meronymy) relationships using large language models (LLMs). It is the first work to apply LLMs to fine-grained product ontology building, leveraging prompt engineering and an automated reasoning pipeline to directly identify and structure meronymic relations from unstructured text—such as user reviews. A novel “LLM-as-a-judge” paradigm is introduced to evaluate ontology quality without human annotation, enabling lightweight supervision. Experiments demonstrate that our approach significantly outperforms BERT-based baselines in both relation extraction accuracy and ontology completeness, validating the effectiveness and practicality of LLMs for ontology construction under low-supervision, high-generalization settings.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Information Extraction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Ontologies have become essential in today's digital age as a way of organising the vast amount of readily available unstructured text. In providing formal structure to this information, ontologies have immense value and application across various domains, e.g., e-commerce, where countless product listings necessitate proper product organisation. However, the manual construction of these ontologies is a time-consuming, expensive and laborious process. In this paper, we harness the recent advancements in large language models (LLMs) to develop a fully-automated method of extracting product ontologies, in the form of meronymies, from raw review texts. We demonstrate that the ontologies produced by our method surpass an existing, BERT-based baseline when evaluating using an LLM-as-a-judge. Our investigation provides the groundwork for LLMs to be used more generally in (product or otherwise) ontology extraction.

Problem

• Automating meronymic ontology extraction from unstructured text
• Reducing manual effort in product taxonomy construction
• Improving ontology quality using large language models

Innovation

• Uses large language models for ontology extraction
• Automates meronymy extraction from raw review texts
• Outperforms BERT-based baseline with LLM evaluation