A Grounded Interaction Protocol for Explainable Artificial Intelligence
Prashan Madumal, Tim Miller, Liz Sonenberg, Frank Vetere
Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS | ASSOC COMPUTING MACHINERY | Published : 2019
Explainable Artificial Intelligence (XAI) systems need to include an explanation model to communicate the internal decisions, behaviours and actions to the interacting humans. Successful explanation involves both cognitive and social processes. In this paper we focus on the challenge of meaningful interaction between an explainer and an explainee and investigate the structural aspects of an interactive explanation to propose an interaction protocol. We follow a bottom-up approach to derive the model by analysing transcripts of different explanation dialogue types with 398 explanation dialogues. We use grounded theory to code and identify key components of an explanation dialogue. We formaliz..View full abstract
The research described in this paper was supported by the University of Melbourne research scholarship (MRS); SocialNUI: Microsoft Research Centre for Social Natural User Interfaces at the University of Melbourne; and a Sponsored Research Collaboration grant from the Commonwealth of Australia Defence Science and Technology Group and the Defence Science Institute, an initiative of the State Government of Victoria. We also acknowledge the support of Joshua Newn and Ronal Singh, given in conducting the study.