elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Conversational Interfaces for Explainable AI: A Human-Centred Approach

Jentzsch, Sophie F. and Höhn, Sviatlana and Hochgeschwender, Nico (2019) Conversational Interfaces for Explainable AI: A Human-Centred Approach. In: AAMAS 2019 Workshop on EXplainable TRansparent Autonomous Agents and Multi-Agent Systems (EXTRAAMAS19), pp. 77-92. Springer. 1st International Workshop on EXplainable TRansparent Autonomous Agents and Multi-Agent Systems (EXTRAAMAS 2019), 13.-14. May 2019, Montreal, Canada.

[img] PDF - Registered users only
4MB

Abstract

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 directly from an intelligent agent. We propose Conversational Interfaces (CIs) to be the perfect setting, since they are intuitive for humans and computationally processible. While there are many approaches addressing technical and agent related issues of this human-agent communication problem, the user perspective appears to be widely neglected. With the goal of better requirement understanding and identification of implicit user expectations, a Wizard of Oz (WoZ) experiment was conducted, where participants tried to elicit basic information from a pretended artificial agent via Conversational Interface (What are your capabilities?). Chats were analysed by means of Conversation Analysis, where the hypothesis that users pursue fundamentally different strategies could be verified. Stated 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 inferred essential indications for the implementation of such a CI. The findings show that existing intent-based design of Conversational Interfaces is very limited, even in a well-defined task-based interaction.

Item URL in elib:https://elib.dlr.de/128143/
Document Type:Conference or Workshop Item (Speech)
Title:Conversational Interfaces for Explainable AI: A Human-Centred Approach
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Jentzsch, Sophie F.Sophie.Jentzsch (at) dlr.dehttps://orcid.org/0000-0001-6217-8814
Höhn, Sviatlanasviatlana.hoehn (at) uni.luUNSPECIFIED
Hochgeschwender, NicoNico.Hochgeschwender (at) dlr.dehttps://orcid.org/0000-0003-1306-7880
Date:2019
Journal or Publication Title:AAMAS 2019 Workshop on EXplainable TRansparent Autonomous Agents and Multi-Agent Systems (EXTRAAMAS19)
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Page Range:pp. 77-92
Publisher:Springer
Series Name:Lecture Notes in Artificial Intelligence (LNAI)
Status:Published
Keywords:Explainability ; XAI ; Human-Agent Interaction ; Conversational Interface ; Wizard of Oz
Event Title:1st International Workshop on EXplainable TRansparent Autonomous Agents and Multi-Agent Systems (EXTRAAMAS 2019)
Event Location:Montreal, Canada
Event Type:Workshop
Event Dates:13.-14. May 2019
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Technik für Raumfahrtsysteme
DLR - Research theme (Project):R - Vorhaben SISTEC
Location: Köln-Porz
Institutes and Institutions:Institut of Simulation and Software Technology
Institut of Simulation and Software Technology > Distributed Systems and Component Software
Deposited By: Jentzsch, Sophie Freya
Deposited On:30 Oct 2019 11:13
Last Modified:30 Oct 2019 11:13

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.