IRUS Total

Data-empowered argumentation for dialectically explainable predictions

File Description SizeFormat 
ECAI_2020_paper_1344.pdfFile embargoed until 01 January 100002.04 MBAdobe PDF
Title: Data-empowered argumentation for dialectically explainable predictions
Authors: Cocarascu, O
Stylianou, A
Cyras, K
Toni, F
Item Type: Conference Paper
Abstract: Today’s AI landscape is permeated by plentiful data anddominated by powerful data-centric methods with the potential toimpact a wide range of human sectors. Yet, in some settings this po-tential is hindered by these data-centric AI methods being mostlyopaque. Considerable efforts are currently being devoted to defin-ing methods for explaining black-box techniques in some settings,while the use of transparent methods is being advocated in others,especially when high-stake decisions are involved, as in healthcareand the practice of law. In this paper we advocate a novel transpar-ent paradigm of Data-Empowered Argumentation (DEAr in short)for dialectically explainable predictions. DEAr relies upon the ex-traction of argumentation debates from data, so that the dialecticaloutcomes of these debates amount to predictions (e.g. classifications)that can be explained dialectically. The argumentation debates con-sist of (data) arguments which may not be linguistic in general butmay nonetheless be deemed to be ‘arguments’ in that they are dialec-tically related, for instance by disagreeing on data labels. We illus-trate and experiment with the DEAr paradigm in three settings, mak-ing use, respectively, of categorical data, (annotated) images and text.We show empirically that DEAr is competitive with another transpar-ent model, namely decision trees (DTs), while also providing natu-rally dialectical explanations.
Date of Acceptance: 14-Jan-2020
URI: http://hdl.handle.net/10044/1/77585
Publisher: IOS Press
Copyright Statement: This paper is embargoed until publication.
Conference Name: 24th European Conference on Artificial Intelligence (ECAI 2020)
Publication Status: Accepted
Start Date: 2020-08-29
Finish Date: 2020-09-02
Conference Place: Santiago de Compostela, Spain
Embargo Date: publication subject to indefinite embargo
Appears in Collections:Computing
Faculty of Engineering