The purpose of this project is to develop an architecture for AI dialogue systems that is "ethical" in the sense that it is inspired by ethical principles and values. In particular, the architecture combines NLP techniques and computational argumentation to ensure that user data are ethically managed, the reasoning process is consistent, and the answer is explainable. To illustrate the system, we focused on a case study regarding COVID-19 vaccine information.
This micro-project was jointly performed by Consiglio Nazionale delle Ricerche (CNR, Bettina Fazzinga) and Università di Bologna (UNIBO, Andrea Galassi and Paolo Torroni). The project is part of the Humane-AI-Net network of excellent research centers in AI.