@ARTICLE{Potoniec_J._Learning_2020, author={Potoniec, J.}, volume={68}, number={No. 6}, journal={Bulletin of the Polish Academy of Sciences Technical Sciences}, pages={1481-1490}, howpublished={online}, year={2020}, 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.}, type={Article}, title={Learning OWL 2 Property Characteristics as an Explanation for an RNN}, URL={http://www.czasopisma.pan.pl/Content/117659/PDF/23_D1481-1490_01383_Bpast.No.68-6_29.12.20_OK.pdf}, doi={10.24425/bpasts.2020.134625}, keywords={recurrent neural networks, ontology learning, property characteristics, knowledge graphs, semantic web, deep learning}, }