Anjana Wijekoon
CBR driven interactive explainable AI.
Wijekoon, Anjana; Wiratunga, Nirmalie; Martin, Kyle; Corsar, David; Nkisi-Orji, Ikechukwu; Palihawadana, Chamath; Bridge, Derek; Pradeep, Preeja; Diaz Agudo, Belen; Caro-Martínez, Marta
Authors
Professor Nirmalie Wiratunga n.wiratunga@rgu.ac.uk
Associate Dean for Research
Dr Kyle Martin k.martin3@rgu.ac.uk
Lecturer
Dr David Corsar d.corsar1@rgu.ac.uk
Senior Lecturer
Dr Ikechukwu Nkisi-Orji i.nkisi-orji@rgu.ac.uk
Chancellor's Fellow
Mr Chamath Palihawadana c.palihawadana@rgu.ac.uk
Research Assistant
Derek Bridge
Preeja Pradeep
Belen Diaz Agudo
Marta Caro-Martínez
Abstract
Explainable AI (XAI) can greatly enhance user trust and satisfaction in AI-assisted decision-making processes. Numerous explanation techniques (explainers) exist in the literature, and recent findings suggest that addressing multiple user needs requires employing a combination of these explainers. We refer to such combinations as explanation strategies. This paper introduces iSee - Intelligent Sharing of Explanation Experience, an interactive platform that facilitates the reuse of explanation strategies and promotes best practices in XAI by employing the Case-based Reasoning (CBR) paradigm. iSee uses an ontology-guided approach to effectively capture explanation requirements, while a behaviour tree-driven conversational chatbot captures user experiences of interacting with the explanations and provides feedback. In a case study, we illustrate the iSee CBR system capabilities by formalising a realworld radiograph fracture detection system and demonstrating how each interactive tools facilitate the CBR processes.
Citation
WIJEKOON, A., WIRATUNGA, N., MARTIN, K., CORSAR, D., NKISI-ORJI, I., PALIHAWADANA, C., BRIDGE, D., PRADEEP, P., AGUDO, B.D. and CARO-MARTÍNEZ, M. 2023. CBR driven interactive explainable AI. In MASSIE, S. and CHAKRABORTI, S. (eds.) 2023. Case-based reasoning research and development: proceedings of the 31st International conference on case-based reasoning 2023, (ICCBR 2023), 17-20 July 2023, Aberdeen, UK. Lecture notes in computer science (LNCS), 14141. Cham: Springer [online], pages169-184. Available from: https://doi.org/10.1007/978-3-031-40177-0_11
Presentation Conference Type | Conference Paper (published) |
---|---|
Conference Name | 31st International conference on case-based reasoning 2023 (ICCBR 2023): CBR in a data-driven world |
Start Date | Jul 17, 2023 |
End Date | Jul 20, 2023 |
Acceptance Date | Jun 16, 2023 |
Online Publication Date | Jul 30, 2023 |
Publication Date | Sep 30, 2023 |
Deposit Date | Jul 4, 2023 |
Publicly Available Date | Jul 31, 2024 |
Publisher | Springer |
Peer Reviewed | Peer Reviewed |
Pages | 169-184 |
Series Title | Lecture notes in computer science (LNCS) |
Series Number | 14141 |
Series ISSN | 0302-9743; 1611-3349 |
Book Title | Case-based reasoning research and development: proceedings of the 31st International conference on case-based reasoning 2023, (ICCBR 2023), 17-20 July 2023, Aberdeen, UK |
ISBN | 9783031401763 |
DOI | https://doi.org/10.1007/978-3-031-40177-0_11 |
Keywords | Interactive XAI; Ontology-based CBR; Conversational AI |
Public URL | https://rgu-repository.worktribe.com/output/1976835 |
Files
WIJEKOON 2023 CBR driven interactive (AAM)
(10.5 Mb)
PDF
You might also like
Failure-driven transformational case reuse of explanation strategies in CloodCBR.
(2023)
Presentation / Conference Contribution
Explainable weather forecasts through an LSTM-CBR twin system.
(2023)
Presentation / Conference Contribution
Introducing Clood CBR: a cloud based CBR framework.
(2023)
Presentation / Conference Contribution
iSee: intelligent sharing of explanation experiences.
(2023)
Presentation / Conference Contribution
iSee: intelligent sharing of explanation experience of users for users.
(2023)
Presentation / Conference Contribution
Downloadable Citations
About OpenAIR@RGU
Administrator e-mail: publications@rgu.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search