City Research Online

Abstract

Knowledge graphs feature ever more frequently as symbolic components in neurosymbolic research and systems. But even though a central concern of neurosymbolic AI is to combine neural learning with symbolic reasoning, relatively little neurosymbolic research focuses on leveraging the logical representation and reasoning capabilities of OWL-based knowledge graphs. The objective of this position paper is to inspire more neurosymbolic researchers to embrace the OWL and the Semantic Web by raising awareness of the benefits, capabilities, and applications of OWL-based knowledge graphs, particularly with respect to logical reasoning. We describe the ecosystem of open W3C standards-based resources available that support the adoption and use of OWL-based knowledge graphs; we describe tools that exist for engineering custom OWL ontologies tailored to particular research needs; we discuss the encoding of background KG knowledge in subsymbolic embedding spaces and various applications of this approach; we discuss and illustrate the reasoning capabilities of OWL-based knowledge graphs; and we describe several promising directions for research that focus on leveraging these reasoning capabilities. We also discuss the specialised resources needed to undertake research on OWL-based knowledge graphs in neurosymbolic systems. We use the example of NeSy4VRD, an image dataset with a custom-designed companion OWL ontology. The scarcity of this kind of resource should be addressed to accelerate research in this field.

Publication Type:	Article
Publisher Keywords:	neurosymbolic, AI, deep learning, Semantic Web, OWL, ontologies, knowledge graphs, reasoning
Departments:	School of Science & Technology School of Science & Technology > Computer Science
SWORD Depositor:	Symplectic Administrator

Export

Downloads