Conceptual modelling of explanation experiences through the iSeeonto ontology.

Caro-Martínez, Marta; Wijekoon, Anjana; Recio-García, Juan A.; Corsar, David; Nkisi-Orji, Ikechukwu

Abstract

Explainable Artificial Intelligence is a big research field required in many situations where we need to understand Artificial Intelligence behaviour. However, each explanation need is unique which makes it difficult to apply explanation techniques and solutions that are already implemented when faced with a new problem. Therefore, the task to implement an explanation system can be very challenging because we need to take the AI model into account, user's needs and goals, available data, suitable explainers, etc. In this work, we propose a formal model to define and orchestrate all the elements involved in an explanation system, and make a novel contribution regarding the formalisation of this model as the iSeeOnto ontology. This ontology not only enables the conceptualisation of a wide range of explanation systems, but also supports the application of Case-Based Reasoning as a knowledge transfer approach that reuses previous explanation experiences from unrelated domains. To demonstrate the suitability of the proposed model, we present an exhaustive validation by classifying reference explanation systems found in the literature into the iSeeOnto ontology.

Citation

CARO-MARTÍNEZ, M., WIJEKOON, A., RECIO-GARCÍA, J.A., CORSAR, D. and NKISI-ORJI, I. 2022. Conceptual modelling of explanation experiences through the iSeeonto ontology. In Reuss, P. and Schönborn, J. (eds.) Workshop proceedings of the 30th International conference on case-based reasoning (ICCBR-WS 2022), 12-15 September 2022, Nancy, France. CEUR workshop proceedings, 3389. Aachen: CEUR-WS [online], pages 117-128. Available from: https://ceur-ws.org/Vol-3389/ICCBR_2022_Workshop_paper_86.pdf

• Presentation Conference Type: Conference Paper (published)
• Conference Name: Workshops of the 30th International conference on case-based reasoning (ICCBR-WS 2022)
• Start Date: Sep 12, 2022
• End Date: Sep 15, 2022
• Acceptance Date: Jul 22, 2022
• Online Publication Date: May 11, 2023
• Publication Date: May 11, 2023
• Deposit Date: Jun 2, 2023
• Publicly Available Date: Jun 2, 2023
• Journal: CEUR Workshop Proceedings
• Print ISSN: 1613-0073
• Publisher: CEUR-WS
• Peer Reviewed: Peer Reviewed
• Pages: 117-128
• Series Title: CEUR workshop proceedings
• Series Number: 3389
• Series ISSN: 1613-0073
• Keywords: XAI; Ontology; Conceptual model; CBR
• Public URL: https://rgu-repository.worktribe.com/output/1977681
• Publisher URL: https://ceur-ws.org/Vol-3389/ICCBR_2022_Workshop_paper_86.pdf