A Model of Explanations for User-Centered AI - arXiv

文章推薦指數: 80 %
投票人數:10人

Computer Science > Artificial Intelligence. arXiv:2010.01479 (cs). [Submitted on 4 Oct 2020]. Title:Explanation Ontology: A Model of Explanations for ... GlobalSurvey Injust3minutes,helpusbetterunderstandhowyouperceivearXiv. Takethesurvey TAKESURVEY ComputerScience>ArtificialIntelligence arXiv:2010.01479(cs) [Submittedon4Oct2020] Title:ExplanationOntology:AModelofExplanationsforUser-CenteredAI Authors:ShruthiChari,OshaniSeneviratne,DanielM.Gruen,MorganA.Foreman,AmarK.Das,DeborahL.McGuinness DownloadPDF Abstract:ExplainabilityhasbeenagoalforArtificialIntelligence(AI)systemssince theirconception,withtheneedforexplainabilitygrowingasmorecomplexAI modelsareincreasinglyusedincritical,high-stakessettingssuchas healthcare.ExplanationshaveoftenaddedtoanAIsysteminanon-principled, post-hocmanner.Withgreateradoptionofthesesystemsandemphasison user-centricexplainability,thereisaneedforastructuredrepresentation thattreatsexplainabilityasaprimaryconsideration,mappingenduserneeds tospecificexplanationtypesandthesystem'sAIcapabilities.Wedesignan explanationontologytomodelboththeroleofexplanations,accountingforthe systemanduserattributesintheprocess,andtherangeofdifferent literature-derivedexplanationtypes.Weindicatehowtheontologycansupport userrequirementsforexplanationsinthedomainofhealthcare.Weevaluateour ontologywithasetofcompetencyquestionsgearedtowardsasystemdesigner whomightuseourontologytodecidewhichexplanationtypestoinclude,given acombinationofusers'needsandasystem'scapabilities,bothinsystem designsettingsandinreal-timeoperations.Throughtheuseofthisontology, systemdesignerswillbeabletomakeinformedchoicesonwhichexplanationsAI systemscanandshouldprovide. Comments: 16pages(but1referenceoveronarxiv),5tables,3codelistings,1figure Subjects: ArtificialIntelligence(cs.AI);Human-ComputerInteraction(cs.HC);MachineLearning(cs.LG) Journal reference: InternationalSemanticWebConference(ISWC),2020 Citeas: arXiv:2010.01479[cs.AI]   (or arXiv:2010.01479v1[cs.AI]forthisversion) SubmissionhistoryFrom:ShruthiChari[viewemail] [v1] Sun,4Oct202003:53:35UTC(2,796KB) Full-textlinks: Download: PDF Otherformats Currentbrowsecontext:cs.AI new | recent | 2010 Changetobrowseby: cs cs.HC cs.LG References&Citations NASAADSGoogleScholar SemanticScholar DBLP-CSBibliography listing|bibtex ShruthiChariOshaniSeneviratneAmarK.DasDeborahL.McGuinness a exportbibtexcitation Loading... Bibtexformattedcitation × loading... Dataprovidedby: Bookmark BibliographicTools BibliographicandCitationTools BibliographicExplorerToggle BibliographicExplorer(WhatistheExplorer?) LitmapsToggle Litmaps(WhatisLitmaps?) scite.aiToggle sciteSmartCitations(WhatareSmartCitations?) Code&Data CodeandDataAssociatedwiththisArticle arXivLinkstoCodeToggle arXivLinkstoCode&Data(WhatisLinkstoCode&Data?) RelatedPapers RecommendersandSearchTools ConnectedPapersToggle ConnectedPapers(WhatisConnectedPapers?) Corerecommendertoggle CORERecommender(WhatisCORE?) AboutarXivLabs arXivLabs:experimentalprojectswithcommunitycollaborators arXivLabsisaframeworkthatallowscollaboratorstodevelopandsharenewarXivfeaturesdirectlyonourwebsite. BothindividualsandorganizationsthatworkwitharXivLabshaveembracedandacceptedourvaluesofopenness,community,excellence,anduserdataprivacy.arXiviscommittedtothesevaluesandonlyworkswithpartnersthatadheretothem. HaveanideaforaprojectthatwilladdvalueforarXiv'scommunity?LearnmoreaboutarXivLabsandhowtogetinvolved. Whichauthorsofthispaperareendorsers?| DisableMathJax(WhatisMathJax?)



請為這篇文章評分?