Author:
Axelsson Agnes,Buschmeier Hendrik,Skantze Gabriel
Abstract
Intelligent agents interacting with humans through conversation (such as a robot, embodied conversational agent, or chatbot) need to receive feedback from the human to make sure that its communicative acts have the intended consequences. At the same time, the human interacting with the agent will also seek feedback, in order to ensure that her communicative acts have the intended consequences. In this review article, we give an overview of past and current research on how intelligent agents should be able to both give meaningful feedback toward humans, as well as understanding feedback given by the users. The review covers feedback across different modalities (e.g., speech, head gestures, gaze, and facial expression), different forms of feedback (e.g., backchannels, clarification requests), and models for allowing the agent to assess the user's level of understanding and adapt its behavior accordingly. Finally, we analyse some shortcomings of current approaches to modeling feedback, and identify important directions for future research.
Funder
Stiftelsen för Strategisk Forskning
Deutsche Forschungsgemeinschaft
Reference189 articles.
1. The theory of planned behavior;Ajzen;Organ. Behav. Hum. Decis. Process,1991
2. Generating robot/agent backchannels during a storytelling experiment,;Al Moubayed,2009
3. AllenJ.
CoreM. G.
Draft of DAMSL: Dialog Act Markup in Several Layers1997
4. Om det svenska systemet för språklig återkoppling,;Allwood,1988
5. A study of gestural feedback expressions,;Allwood,2003
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献