Ontolearn-A Framework for Large-scale OWL Class Expression Learning in Python
This framework addresses the problem of scalable and interpretable class expression learning for researchers and practitioners in semantic web and knowledge graph domains, representing an incremental integration of existing methods into a unified tool.
The authors introduced Ontolearn, a Python framework for learning OWL class expressions from large knowledge graphs, integrating state-of-the-art symbolic and neuro-symbolic learners like EvoLearner and DRILL, and including features such as an LLM-based verbalization module and SPARQL query mapping for remote triplestore operation.
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.