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.

Argumentation and Logic Programming for Explainable and Ethical AI / Roberta Calegari, Andrea Omicini, Giovanni Sartor. - ELETTRONICO. - 2742:(2020), pp. 55-68. (Intervento presentato al convegno XAI.it 2020 – Italian Workshop on Explainable Artificial Intelligence 2020 tenutosi a Online event nel 25-26 November 2020).

Argumentation and Logic Programming for Explainable and Ethical AI

Roberta Calegari;Andrea Omicini;Giovanni Sartor
2020

Abstract

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.
2020
XAI.it 2020 – Italian Workshop on Explainable Artificial Intelligence 2020
55
68
Argumentation and Logic Programming for Explainable and Ethical AI / Roberta Calegari, Andrea Omicini, Giovanni Sartor. - ELETTRONICO. - 2742:(2020), pp. 55-68. (Intervento presentato al convegno XAI.it 2020 – Italian Workshop on Explainable Artificial Intelligence 2020 tenutosi a Online event nel 25-26 November 2020).
Roberta Calegari, Andrea Omicini, Giovanni Sartor
File in questo prodotto:
File Dimensione Formato  
paper5.pdf

accesso aperto

Descrizione: PDF editoriale
Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 689.52 kB
Formato Adobe PDF
689.52 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/780458
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? ND
social impact