Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

On the Use of Large Language Models to Generate Capability Ontologies

Luis Miguel Vieira da Silva, Aljosha Köcher, Felix Gehlhoff, Alexander Fay

TL;DR

This paper investigates how LLMs can be used to create capability ontologies using a semi-automated approach based on RDF syntax checking, OWL reasoning, and SHACL constraints.

Abstract

Capability ontologies are increasingly used to model functionalities of systems or machines. The creation of such ontological models with all properties and constraints of capabilities is very complex and can only be done by ontology experts. However, Large Language Models (LLMs) have shown that they can generate machine-interpretable models from natural language text input and thus support engineers / ontology experts. Therefore, this paper investigates how LLMs can be used to create capability ontologies. We present a study with a series of experiments in which capabilities with varying complexities are generated using different prompting techniques and with different LLMs. Errors in the generated ontologies are recorded and compared. To analyze the quality of the generated ontologies, a semi-automated approach based on RDF syntax checking, OWL reasoning, and SHACL constraints is used. The results of this study are very promising because even for complex capabilities, the generated ontologies are almost free of errors.

On the Use of Large Language Models to Generate Capability Ontologies

TL;DR

This paper investigates how LLMs can be used to create capability ontologies using a semi-automated approach based on RDF syntax checking, OWL reasoning, and SHACL constraints.

Abstract

Capability ontologies are increasingly used to model functionalities of systems or machines. The creation of such ontological models with all properties and constraints of capabilities is very complex and can only be done by ontology experts. However, Large Language Models (LLMs) have shown that they can generate machine-interpretable models from natural language text input and thus support engineers / ontology experts. Therefore, this paper investigates how LLMs can be used to create capability ontologies. We present a study with a series of experiments in which capabilities with varying complexities are generated using different prompting techniques and with different LLMs. Errors in the generated ontologies are recorded and compared. To analyze the quality of the generated ontologies, a semi-automated approach based on RDF syntax checking, OWL reasoning, and SHACL constraints is used. The results of this study are very promising because even for complex capabilities, the generated ontologies are almost free of errors.
Paper Structure (8 sections, 2 figures, 4 tables)

This paper contains 8 sections, 2 figures, 4 tables.

Table of Contents

  1. Introduction
  2. State of the Art
  3. Background
  4. Related Work
  5. Capability Ontology
  6. Study Design
  7. Results
  8. Conclusion

Figures (2)

  • Figure 1: Simplified representation of a transport capability and its properties modeled with the CaSk ontology. All nodes are individuals (class names in bold).
  • Figure 2: Completeness of the generated ontologies. A value of 1 means that all triples to be created have been generated correctly.