Meronymic Ontology Extraction via Large Language Models
This addresses the time-consuming and expensive process of ontology construction for domains like e-commerce, though it is incremental as it builds on existing LLM capabilities.
The paper tackled the problem of manually constructing ontologies by developing a fully-automated method using large language models (LLMs) to extract product ontologies from raw review texts, and demonstrated that the resulting ontologies surpass a BERT-based baseline as evaluated by an LLM-as-a-judge.
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.