CBR driven interactive explainable AI

Simple item page
dc.check.date2024-07-30en
dc.check.infoAccess to this article is restricted until 12 months after publication by request of the publisheren
dc.contributor.authorWijekoon, Anjanaen
dc.contributor.authorWiratunga, Nirmalieen
dc.contributor.authorMartin, Kyleen
dc.contributor.authorCorsar, Daviden
dc.contributor.authorNkisi-Orji, Ikechukwuen
dc.contributor.authorPalihawadana, Chamathen
dc.contributor.authorBridge, Derek G.en
dc.contributor.authorPradeep, Preejaen
dc.contributor.authorDiaz Agudo, Belenen
dc.contributor.authorCaro-Martínez, Martaen
dc.contributor.editorMassie, Stewarten
dc.contributor.editorChakraborti, Sutanuen
dc.contributor.funderEuropean Commissionen
dc.contributor.funderEngineering and Physical Sciences Research Councilen
dc.contributor.funderIrish Research Councilen
dc.date.accessioned2023-10-11T09:28:10Z
dc.date.available2023-10-11T09:28:10Z
dc.date.issued2023-07-30en
dc.description.abstractExplainable 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 real-world radiograph fracture detection system and demonstrating how each interactive tools facilitate the CBR processes.en
dc.description.sponsorshipEuropean Commission (iSee project); Engineering and Physical Sciences Research Council (Grant number EP/V061755/1); Irish Research Council (Grant number CHIST-ERA-2019-iSee); MCIN/AEI and European Union (NextGenerationEU/PRTR Grant number PCI2020-120720-2)en
dc.description.statusPeer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationWijekoon, A., Wiratunga, N., Martin, K., Corsar, D., Nkisi-Orji, I., Palihawadana, C., Bridge, D., Pradeep, P., Diaz Agudo, B. and Caro-Martínez, M. (2023) 'CBR driven interactive explainable AI', in Massie, S. and Chakraborti, S. (eds) Case-Based Reasoning Research and Development. ICCBR 2023, Lecture Notes in Computer Science, 14141, pp. 169-184. Springer, Cham. https://doi.org/10.1007/978-3-031-40177-0_11en
dc.identifier.doihttps://doi.org/10.1007/978-3-031-40177-0_11en
dc.identifier.endpage184en
dc.identifier.isbn9783031401763en
dc.identifier.isbn9783031401770en
dc.identifier.issn0302-9743en
dc.identifier.issn1611-3349en
dc.identifier.journaltitleLecture Notes in Computer Scienceen
dc.identifier.startpage169en
dc.identifier.urihttps://hdl.handle.net/10468/15099
dc.identifier.volume14141en
dc.language.isoenen
dc.publisherSpringer Nature Switzerland AGen
dc.relation.ispartofCase-Based Reasoning Research and Developmenten
dc.relation.ispartofLecture Notes in Computer Scienceen
dc.relation.ispartof31st International conference on case-based reasoning 2023 (ICCBR-2023): CBR in a data-driven world, 17-20 July 2023, Aberdeen, UK. Aberdeen: ICCBR [online], paper 70.en
dc.rights© 2023, the Authors, under exclusive license to Springer Nature Switzerland AG. This is a post-peer-review, pre-copyedit version of a paper published as: Wijekoon, A. et al. (2023). CBR Driven Interactive Explainable AI. In: Massie, S., Chakraborti, S. (eds) Case-Based Reasoning Research and Development. ICCBR 2023. Lecture Notes in Computer Science, vol 14141. Springer, Cham Springer, Cham. The final authenticated version is available online at: https://doi.org/10.1007/978-3-031-40177-0_11en
dc.subjectInteractive XAIen
dc.subjectOntology-based CBRen
dc.subjectConversational AIen
dc.titleCBR driven interactive explainable AIen
dc.typeConference itemen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
paper_70.pdf
Size:
9.84 MB
Format:
Adobe Portable Document Format
Description:
Accepted Version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Insight Centre for Data Analytics - Conference Items
Computer Science - Conference Items