@inproceedings{Cocarascu:2020:10.3233/FAIA200377,
author = {Cocarascu, O and Stylianou, A and Cyras, K and Toni, F},
doi = {10.3233/FAIA200377},
pages = {2449--2456},
publisher = {IOS Press},
title = {Data-empowered argumentation for dialectically explainable predictions},
url = {http://dx.doi.org/10.3233/FAIA200377},
year = {2020}
}

Download

TY  - CPAPER
AB  - 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.
AU  - Cocarascu,O
AU  - Stylianou,A
AU  - Cyras,K
AU  - Toni,F
DO  - 10.3233/FAIA200377
EP  - 2456
PB  - IOS Press
PY  - 2020///
SP  - 2449
TI  - Data-empowered argumentation for dialectically explainable predictions
UR  - http://dx.doi.org/10.3233/FAIA200377
UR  - https://ebooks.iospress.nl/volumearticle/55172
UR  - http://hdl.handle.net/10044/1/77585
ER  - 

Download