NeurOWL: An LLM-Based Neural-symbolic Framework for Incomplete OWL Ontology Reasoning
Artificial Intelligence
Summary
The authors look at a problem where knowledge bases called OWL ontologies are missing some information, making it hard to check if one idea really fits under another (called subsumption). They want to decide if a suggested relationship is believable and explain it by finding what missing facts would make it true. To solve this, the authors created NeurOWL, a smart system that combines logical rules with language models and embeddings to both check and guess missing information. They tested NeurOWL on different real-world knowledge bases and found it works well across multiple fields.
Authors
Hui Yang, Jiaoyan Chen, Yiping Song, Renate Schmidt, Wen Zhang
Abstract
OWL ontologies provide a formal knowledge representation framework that enables semantic reasoning, and have been widely adopted across domains such as healthcare and bioinformatics. In practice, however, real-world ontologies are often incomplete, which pose challenges for reasoning. In this work, we focus on a fundamental subsumption reasoning problem: given an incomplete ontology and a candidate (non-entailed) subsumption, determine whether the subsumption is semantically plausible and, if so, providing a logically sound explanation containing potential missing axioms. This task unifies subsumption verification with ontology abduction, and generalizes the latter by removing the need for a predefined candidate set of missing axioms. To address this subsumption reasoning problem, we propose NeurOWL, an end-to-end neuro-symbolic framework that jointly performs verification and abduction, leveraging both formally defined semantics and textual semantics through Large Language Models and ontology embeddings. We evaluate NeurOWL on real-world ontologies across multiple domains, demonstrating strong and robust performance across different domains.