Ontology engineering with Large Language Models
This work addresses the challenge of ontology engineering for researchers and practitioners in semantic web and knowledge representation, though it is incremental as it applies an existing method (fine-tuning LLMs) to a specific domain task.
The authors tackled the problem of enriching ontologies by automatically translating natural language sentences into Description Logic, using a fine-tuned GPT-3 model to generate OWL Functional Syntax axioms, which were then applied to enhance an ontology with human supervision and made available as a Protégé plugin.
We tackle the task of enriching ontologies by automatically translating natural language sentences into Description Logic. Since Large Language Models (LLMs) are the best tools for translations, we fine-tuned a GPT-3 model to convert Natural Language sentences into OWL Functional Syntax. We employ objective and concise examples to fine-tune the model regarding: instances, class subsumption, domain and range of relations, object properties relationships, disjoint classes, complements, cardinality restrictions. The resulted axioms are used to enrich an ontology, in a human supervised manner. The developed tool is publicly provided as a Protge plugin.