CINECA IRIS Institutional Research Information System
IRIS è l'Anagrafe della ricerca dell'Università degli Studi di Trento, e ha lo scopo di raccogliere, documentare, conservare e diffondere, anche ad accesso aperto, la produzione scientifica degli autori afferenti all'Università degli Studi di Trento.
EnglishRecent advances in artificial intelligence raise a number of concerns. Among the challenges to be addressed by researchers, accountability of artificial intelligence solutions is one of the most critical. This paper focuses on artificial intelligence applications using natural language to investigate if the core semantics defined for a large-scale natural language processing system could assist in addressing accountability issues. Core semantics aims to obtain a full interpretation of the content of natural language texts, representing both implicit and explicit knowledge, using only ‘subj-action-(obj)’ structures and causal, temporal, spatial and personal-world links. The first part of the paper offers a summary of the difficulties to be addressed and of the reasons why representing the meaning of a natural language text is relevant for artificial intelligence accountability. In the second part, a-proof-of-concept for the application of such a knowledge representation to support accountability, and a detailed example of the analysis obtained with a prototype system named CoreSystem is illustrated. While only preliminary, these results give some new insights and indicate that the provided knowledge representation can be used to support accountability, looking inside the box.
Looking Inside the Black Box: Core Semantics Towards Accountability of Artificial Intelligence / Garigliano, Roberto; Mich, Luisa. - STAMPA. - 11865:(2019), pp. 250-266. [10.1007/978-3-030-30985-5_16]
| Titolo: | Looking Inside the Black Box: Core Semantics Towards Accountability of Artificial Intelligence | |
| Autori: | Garigliano, Roberto; Mich, Luisa | |
| Autori Unitn: | ||
| Titolo del volume contenente il saggio: | From Software Engineering to Formal Methods and Tools, and Back | |
| Luogo di edizione: | Cham | |
| Casa editrice: | Springer | |
| Anno di pubblicazione: | 2019 | |
| ISBN: | 978-3-030-30984-8 | |
| Handle: | http://hdl.handle.net/11572/243752 | |
| Citazione: | Looking Inside the Black Box: Core Semantics Towards Accountability of Artificial Intelligence / Garigliano, Roberto; Mich, Luisa. - STAMPA. - 11865:(2019), pp. 250-266. [10.1007/978-3-030-30985-5_16] | |
| Appare nelle tipologie: | 02.1 Saggio su volume miscellaneo o Capitolo di libro (Essay or Book Chapter) |
File in questo prodotto:
| File | Descrizione | Tipologia | Licenza | |
|---|---|---|---|---|
| Garigliano Mich Core semantics for AI Accountability.pdf | Capitolo del libro | Post-print referato (Refereed author’s manuscript) | Tutti i diritti riservati (All rights reserved) | Administrator |
Copyright © 2022