Learning OWL 2 Property Characteristics as an Explanation for an RNN

Abstract

We propose an approach to indirectly learn the Web Ontology Language OWL 2 property characteristics as an explanation for a deep recurrent neural network (RNN). The input is a knowledge graph represented in Resource Description Framework (RDF) and the output are scored axioms representing the characteristics. The proposed method is capable of learning all the characteristics included in OWL 2: functional, inverse functional, reflexive and irreflexive, symmetric and asymmetric, transitive. We report and discuss experimental evaluation on DBpedia 2016-10, showing that the proposed approach has advantages over a simple counting baseline.

Keywords

• recurrent neural networks
• ontology learning
• property characteristics
• knowledge graphs
• semantic web
• deep learning