On the Multiple Roles of Ontologies in Explainable AI

TL;DR

This paper explores how ontologies can enhance Explainable AI by supporting reference modeling, reasoning, and knowledge refinement, highlighting current approaches and future challenges for human-centric explanations.

Contribution

It identifies three key roles of ontologies in XAI and provides a structured overview of existing methods and challenges for ontology-based explanations.

Findings

Ontologies support reference modeling, reasoning, and knowledge refinement in XAI.

Current approaches vary across the three roles, with ongoing challenges.

Future work needed to evaluate human-understandability of ontology-based explanations.

Abstract

This paper discusses the different roles that explicit knowledge, in particular ontologies, can play in Explainable AI and in the development of human-centric explainable systems and intelligible explanations. We consider three main perspectives in which ontologies can contribute significantly, namely reference modelling, common-sense reasoning, and knowledge refinement and complexity management. We overview some of the existing approaches in the literature, and we position them according to these three proposed perspectives. The paper concludes by discussing what challenges still need to be addressed to enable ontology-based approaches to explanation and to evaluate their human-understandability and effectiveness.