Explainable AI via Computational Argumentation

Описание: Francesca Toni, Professor at the Imperial College London, is the speaker of the lecture organized by EMbeDS (Monday June 28, 2021, h 15:00-16:30). The seminar will take place online, live streaming on the Youtube channel of Sant'Anna School

Explainable AI (XAI) has been investigated for decades and, together with AI itself, has witnessed unprecedented growth in recent years, fuelled by data availability and computational power. Indeed, it is widely acknowledged that AI cannot fully benefit society without addressing its widespread inability to explain its outputs, causing human mistrust and doubts regarding regulatory compliance. Among various approaches to XAI, argumentative models have been advocated in both the AI and social science literature, as their dialectical nature appears to match some basic desirable features of the explanation activity.
Computational argumentation is a well-established paradigm in AI, at the intersection of knowledge representation and reasoning, computational linguistics and multi-agent systems. It is based on defining argumentation frameworks comprising sets of arguments and dialectical relations between them (e.g., of attack and, in addition or instead, of support), as well as so-called semantics (e.g., amounting to definitions of dialectically acceptable sets of arguments or of dialectical strength of arguments) with accompanying computational machinery.
In this talk I will show how computational argumentation, combined with a variety of mechanisms for mining argumentation frameworks, can be used to support various forms of XAI.