CEO: Counterfactual Explanations for Ontologies

Tracking #: 3566-4780

Authors: 
Matthieu Bellucci
Nicolas Delestre
Nicolas Malandain
Cecilia Zanni-Merk

Responsible editor: 
Guest Editors Interactive SW 2022

Submission type: 
Full Paper
Abstract: 
Debugging and repairing Web Ontology Language (OWL) ontologies has been a key field of research since OWL became a W3C recommendation. One way to understand errors and fix them is done through explanations. These explanations are usually extracted from the reasoner and displayed to the ontology authors as is. In the meantime, there has been a recent call in the eXplainable AI (XAI) field to use expert knowledge in the form of knowledge graphs and ontologies. In this paper, a parallel between explanations for machine learning and for ontologies is drawn. This link enables the adaptation of XAI methods to explain ontologies and their entailments. Counterfactual explanations have been identified as a good candidate to solve the explainability problem in machine learning. The CEO (Counterfactual Explanations for Ontologies) method is thus proposed to explain inconsistent ontologies using counterfactual explanations. A preliminary user-study is conducted to ensure that using XAI methods for ontologies is relevant and worth pursuing.
Full PDF Version: 
Tags: 
Reviewed

Decision/Status: 
Accept

Solicited Reviews:
Click to Expand/Collapse
Review #1
By Md Kamruzzaman Sarker submitted on 13/Nov/2023
Suggestion:
Accept
Review Comment:

This version of the paper is much improved, thanks to the authors.

One of my concern about the time and scalability is now addressed.

Analysis of the results, effectiveness and the limitations of this approach are discussed, that makes this paper better.

I have increased the review score for this submission.

Review #2
Anonymous submitted on 11/Dec/2023
Suggestion:
Minor Revision
Review Comment:

The authors have successfully addressed language-related comments and enhanced the overall organization of sections, including the introduction, related work, and approach. The motivation behind the limited experimentation is now well articulated. To reflect the exploratory nature, I suggest considering the addition of "towards" in the title, projecting the paper as a step forward in an ongoing exploration.