Arg2P: An argumentation framework for explainable intelligent systems


Roberta Calegari, Giuseppe Pisano, Andrea Omicini, Giovanni Sartor

In this paper we present the computational model of Arg2P, a logic-based argumentation framework for defeasible reasoning and agent conversation particularly suitable for explaining agent intelligent behaviours. The model is reified as the Arg2P technology, which is presented and discussed both from an architectural and a technological perspective so as to point out its potential in the engineering of intelligent systems. Finally, an illustrative application scenario is discussed in the domain of computable law for autonomous vehicles.

(keywords) Arg2P, intelligent systems engineering, explainable intelligent systems, logic- based technology, argumentation, defeasible reasoning, multi-agent systems

Journal of Logic and Computation, November 2021, Oxford University Press.

@article{arg2p-jlc,
author = {Calegari, Roberta and Pisano, Giuseppe and Omicini, Andrea and Sartor, Giovanni},
journal = {Journal of Logic and Computation},
keywords = {Arg2P, intelligent systems engineering, explainable intelligent systems, logic- based technology, argumentation, defeasible reasoning, multi-agent systems},
month = nov,
publisher = {Oxford University Press},
title = {{Arg\textsf{2}P}: An argumentation framework for explainable intelligent systems},
year = 2021}

Journals & Series

Tags: Arg2P

Publication

— authors

Roberta Calegari, Giuseppe Pisano, Andrea Omicini, Giovanni Sartor

— status

camera-ready sent

— sort

article in journal

Venue

— journal

Journal of Logic and Computation

— publication date

November 2021

BibTeX

— BibTeX ID
arg2p-jlc
— BibTeX category
article

Partita IVA: 01131710376 - Copyright © 2008-2021 APICe@DISI Research Group - PRIVACY