Argumentation and Logic Programming for Explainable and Ethical AI


Roberta Calegari  /  Andrea Omicini, Giovanni Sartor, Roberta Calegari

In this paper we sketch a vision of explainability of intelligent systems as a logic approach suitable to be injected into and exploited by the system actors once integrated with sub-symbolic techniques. In particular, we show how argumentation could be combined with different extensions of logic programming – namely, abduction, inductive logic programming, and probabilistic logic programming – to address the issues of explainable AI as well as to address some ethical concerns about AI.

Events

  • 19th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2020) — 24/11/2020–27/11/2020
  • Italian Workshop on Explainable Artificial Intelligence (XAI.it 2020) — 25/11/2020–26/11/2020

Publications

Tags: CompuLaw

Talk

— speakers

— authors

— sort

talk

— language

wgb.gif

Context

XAI.it 2020

— where

Torino

— when

25/11/2020

Links

— external

SlideShare

Partita IVA: 01131710376 - Copyright © 2008-2022 APICe@DISI Research Group - PRIVACY