Conversational Interfaces for Explainable AI: A Human-Centered Approach
English
Jenzsch, Sophie[Deutsches Zentrum für Luft- und Raumfahrt - DLR]
Höhn, Sviatlana[University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) >]
Hochgeschwender, Nico[University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > > ; Deutsches Zentrum für Luft- und Raumfahrt - DLR]
2019
Proceedings of EXTRAAMAS 2019
1-14
Yes
International
EXTRAAMAS
2019-05-13 tot 2019-05-14
Montreal
Canada
[en] Explainable AI ; Conversational Interfaces ; Autonomous Systems
[en] One major goal of Explainable Artificial Intelligence (XAI), in order to enhance trust in technology, is to enable the user to enquire information and explanation about its functionality directly from an intelligent agent. We propose conversational interfaces (CI) to be the perfect setting, since they are intuitive for humans and computationally processible. While there are many approaches addressing technical issues of this human-agent communication problem, the user perspective appears to be widely neglected. With the purpose of better requirement understanding and identification of implicit expectations from a human-centered view, a Wizard of Oz experiment was conducted, where participants tried to elicit basic information from a pretended artificial agent (What are your capabilities?). The hypothesis that users pursue fundamentally different strategies could be verified with the help of Conversation Analysis. Results illustrate the vast variety in human communication and disclose both requirements of users and obstacles in the implementation of protocols for interacting agents. Finally, we infer essential indications for the implementation of such a CI.