Meronymic Ontology Extraction via Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Dekai, Conia, Simone, Rago, Antonio
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909894756532224
author Zhang, Dekai
Conia, Simone
Rago, Antonio
author_facet Zhang, Dekai
Conia, Simone
Rago, Antonio
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13839
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Meronymic Ontology Extraction via Large Language Models
Zhang, Dekai
Conia, Simone
Rago, Antonio
Computation and Language
Artificial Intelligence
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.
title Meronymic Ontology Extraction via Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.13839