A Short Review for Ontology Learning: Stride to Large Language Models Trend

TL;DR

This paper surveys ontology learning from shallow and deep learning perspectives and analyzes how the rise of large language models reshapes the field. It surveys six OL tasks, outlines limitations of traditional methods, and details how LLMs can aid concept and relation extraction, including hierarchical taxonomy induction and non-taxonomic relations. The authors discuss LLM-based approaches, practical tools (e.g., DeepOnto, OntoGPT), and a set of forward-looking directions such as benchmarks, axiom discovery, domain-expert collaboration, and dynamic ontology updating. The work highlights the potential and current constraints of applying LLMs to OL, emphasizing the need for unified evaluation, human-in-the-loop strategies, and robust tooling to realize scalable, high-quality ontologies in real domains.

Abstract

Ontologies provide formal representation of knowledge shared within Semantic Web applications. Ontology learning involves the construction of ontologies from a given corpus. In the past years, ontology learning has traversed through shallow learning and deep learning methodologies, each offering distinct advantages and limitations in the quest for knowledge extraction and representation. A new trend of these approaches is relying on large language models (LLMs) to enhance ontology learning. This paper gives a review in approaches and challenges of ontology learning. It analyzes the methodologies and limitations of shallow-learning-based and deep-learning-based techniques for ontology learning, and provides comprehensive knowledge for the frontier work of using LLMs to enhance ontology learning. In addition, it proposes several noteworthy future directions for further exploration into the integration of LLMs with ontology learning tasks.

Figures (1)

• Figure 1: Ontology Learning Layer Cake eval2