Argumentative Explanations in AI

Half-day tutorial at KR 2020

Monday 14th September 15:50 (CEST)

Francesca Toni & Antonio Rago

As AI becomes ever more ubiquitous in our everyday lives, its ability to explain to and interact with humans is evolving into a critical research area. Explainable AI (XAI) has therefore emerged as a popular topic but its research landscape is currently very fragmented. A general-purpose, systematic approach for addressing the two challenges of explainability and anthropomorphisation in symphony to form the basis of an AI-supported but human-centred society is critical for the success of XAI.

Our tutorial will focus on how argumentation can serve as the driving force of explanations in three different ways, namely: by building explainable systems from scratch with argumentative foundations or by extracting argumentative reasoning from general AI systems or from data thereof. We will provide a comprehensive review of the methods in the literature for extracting argumentative explanations.

The tutorial is aimed at any KR researcher interested in how KR can contribute to the timely field of XAI. It will be self-contained, with basic background on argumentation and XAI provided.

Tutorial Outline

Part 1
(20 mins)
Introduction to XAI
This section will provide a broad introduction to explainable AI, covering the most prominent methods and applications of recent years.
Part 2
(20 mins)
Background on (Abstract, Bipolar, Gradual) Argumentation
This section will cover all of the relevant background from the argumentation literature, including qualitative and quantitative semantics and properties thereof.
Part 3
(20+70 mins)
Argumentative Explanations
In this section we will provide a review of the methods for extracting argumentative explanations from AI systems in the literature. This will include: purpose-built systems for providing explanations with argumentative reasoning capabilities interweaved in their methods, along with methods which concern the extraction of argumentative abstractions of general AI systems or datasets.




Antonio Rago       Francesca Toni