DEXA HAI

Workshop on Dialogue, Explanation and Argumentation for Human-Agent Interaction

An ECAI 2020 workshop - 7th of September 2020

The International Workshop on Dialogue, Explanation and Argumentation in Human-Agent Interaction (DEXA HAI) will focus on the approaches, concepts and applications relevant to supporting dialogue and explainability in the context of human interaction with agent-based systems.


The workshop will focus on the following questions:

  • How to develop methods to facilitate dialogue between humans and agents?

  • How to derive arguments given such dialogues?

  • How to explain the decisions made by the intelligent systems and how humans interact with such systems?

This workshop will particularly cover the use of computational argumentation and argumentation-based dialogue approaches to answer these questions, but will also consider natural language processing work on dialogue which fits into the ``explainability'' theme.


The workshop will bring together researchers from different application domains with the common theme of dialogue and explanation in interactive agent-based systems, as well as computational argumentation in the same theme. We would like to:

  • Explore the different approaches to dialogue in interactive human-agent systems;

  • Investigate methods or approaches to promoting explainability of agent-based decisions in interactive human-agent systems;

  • Explore the application of argumentation-based approaches to supporting dialogue in interactive human-agent systems;

  • Investigate how explainability can be evaluated in the human-agent context.

Agenda

All times are CET and the workshop is hosted in a ZOOM room via the ECAI platform.

10- 10:15 Welcome - DEXA team

10:15 - 11:00 INVITED TALK: Explainable artificial intelligence: beware the inmates running the asylum (or How I learnt to stop worrying and love the social and behavioural sciences) - Tim Miller

11:00 - 11:15 Argumentative Conversational Agents for Polarized Online Debates (link to slides) - Rafik Hadfi & Takayuki Ito

11:15 - 11:45 INVITED TALK: The Long Way towards Natural Language Explanatory Dialogues - Serena Villata

11:45 - 12:15 INVITED TALK: Argumentative explanations for improving recommendations - Oana Cocarascu

12:15 - 12:45 INVITED TALK: MuMMER: Socially Intelligent Human-Robot Interaction in Public Spaces - Mary Ellen Foster

12:45 - 13:00 Explainable AI for Cultural Minds (link to slides) - Hana Kopecka & Jose Such

13:00 - 13:45 LUNCH BREAK

13:45 - 14:15 Episodic Memory in Explainable Decision Support Systems (link to slides) - Maaike de Boer & Mark Neerincx

14:15 - 14:45 INVITED TALK: Towards DEXAHAI using Multi-Agent Programming - Alison Panisson

14:45 - 15:15 INVITED TALK: An argumentation-based approach to generate domain-specific explanations (link to paper)- Nadin Kokciyan

15:15 - 15:45 A Top-level Model of Case-based Argumentation for Explanation (link to slides) - Henry Prakken

15:45 - 16:00 Closing remarks - DEXA Team

Previous Workshop

DEXA HAI 18 - sites.google.com/view/dexahai-18/home