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.
Titolo: | Argumentation and Logic Programming for Explainable and Ethical AI | |
Autore/i: | Roberta Calegari; Andrea Omicini; Giovanni Sartor | |
Autore/i Unibo: | ||
Anno: | 2020 | |
Serie: | ||
Titolo del libro: | XAI.it 2020 – Italian Workshop on Explainable Artificial Intelligence 2020 | |
Pagina iniziale: | 55 | |
Pagina finale: | 68 | |
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. | |
Data stato definitivo: | 5-gen-2021 | |
Appare nelle tipologie: | 4.01 Contributo in Atti di convegno |
File in questo prodotto:
File | Descrizione | Tipo | Licenza | |
---|---|---|---|---|
paper5.pdf | PDF editoriale | Versione (PDF) editoriale | Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY) | Open Access Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.