Ontolearn-A Framework for Large-scale OWL Class Expression Learning in Python

2025-10-13

AI Summary

This study addresses the automated learning of OWL class expressions and their application to instance classification in large-scale knowledge graphs (KGs). We propose a scalable framework that synergistically integrates symbolic learning with neuro-symbolic learning: it incorporates efficient algorithms—including EvoLearner and DRILL—and introduces an LLM-driven natural language generation module to produce human-readable semantic interpretations of learned class expressions. Additionally, we design a SPARQL query translation mechanism enabling semantically consistent querying and reasoning over remote triple stores. Compared to state-of-the-art approaches, our framework significantly improves accuracy, interpretability, and computational efficiency for learning complex OWL class expressions—particularly those involving conjunction, disjunction, complement, and existential restrictions. Empirical evaluation on real-world large-scale KGs demonstrates superior classification performance and practical deployability.

Technology Category

• Knowledge Representation and Reasoning: Description Logics
• Machine Learning: Neuro-Symbolic Learning
• Data Mining & Knowledge Management: Semantic Web

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In this paper, we present Ontolearn-a framework for learning OWL class expressions over large knowledge graphs. Ontolearn contains efficient implementations of recent stateof-the-art symbolic and neuro-symbolic class expression learners including EvoLearner and DRILL. A learned OWL class expression can be used to classify instances in the knowledge graph. Furthermore, Ontolearn integrates a verbalization module based on an LLM to translate complex OWL class expressions into natural language sentences. By mapping OWL class expressions into respective SPARQL queries, Ontolearn can be easily used to operate over a remote triplestore. The source code of Ontolearn is available at https://github.com/dice-group/Ontolearn.

Problem

• Learning OWL class expressions over large knowledge graphs
• Implementing symbolic and neuro-symbolic class expression learners
• Translating complex OWL expressions into natural language

Innovation

• Implements symbolic and neuro-symbolic class expression learners
• Integrates LLM module to verbalize OWL expressions
• Maps OWL expressions to SPARQL for remote triplestore operations