Artykuł w czasopiśmie
Brak miniatury
Licencja
ClosedAccessDostęp zamknięty
 

Towards Grad-CAM Based Explainability in a Legal Text Processing Pipeline

Uproszczony widok
dc.abstract.enExplainable AI (XAI) is a domain focused on providing interpretabil- ity and explainability of a decision-making process. In the domain of law, in addi- tion to system and data transparency, it also requires the (legal-) decision-model transparency and the ability to understand the model’s inner working when arriv- ing at the decision. This paper provides the first approaches to using a popular im- age processing technique, Grad-CAM, to showcase the explainability concept for legal texts. With the help of adapted Grad-CAM metrics, we show the interplay between the choice of embeddings, its consideration of contextual information, and their effect on downstream processing.
dc.affiliationUniwersytet Warszawski
dc.conference.countryCzechy
dc.conference.datefinish2020-12-10
dc.conference.datestart2020-12-09
dc.conference.placeVirtual
dc.conference.seriesInternational Conference on Legal Knowledge and Information Systems
dc.conference.seriesInternational Conference on Legal Knowledge and Information Systems
dc.conference.seriesshortcutJURIX
dc.conference.shortcutJURIX 2020
dc.conference.weblinkhttps://jurix2020.law.muni.cz/
dc.contributor.authorRamakrishna, Shashishekar
dc.contributor.authorGórski, Łukasz
dc.contributor.authorNowosielski, Jędrzej
dc.date.accessioned2024-01-26T11:03:42Z
dc.date.available2024-01-26T11:03:42Z
dc.date.issued2021
dc.description.financePublikacja bezkosztowa
dc.description.volume2891
dc.identifier.urihttps://repozytorium.uw.edu.pl//handle/item/123551
dc.identifier.weblinkhttp://ceur-ws.org/Vol-2891/XAILA-2020_paper_1.pdf
dc.languageeng
dc.pbn.affiliationcomputer and information sciences
dc.relation.pages1-12
dc.rightsClosedAccess
dc.sciencecloudnosend
dc.subject.enLegal Knowledge Representation
dc.subject.enLanguage Models
dc.subject.enGrad-CAM
dc.subject.enHeatMaps
dc.subject.enCNN
dc.titleTowards Grad-CAM Based Explainability in a Legal Text Processing Pipeline
dc.typeJournalArticle
dspace.entity.typePublication