Modeling Feedback in Interaction With Conversational Agents—A Review
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 al...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-03-01
|
| Series: | Frontiers in Computer Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcomp.2022.744574/full |
| _version_ | 1818280284963995648 |
|---|---|
| author | Agnes Axelsson Hendrik Buschmeier Gabriel Skantze |
| author_facet | Agnes Axelsson Hendrik Buschmeier Gabriel Skantze |
| author_sort | Agnes Axelsson |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-12T23:46:47Z |
| format | Article |
| id | doaj.art-19648eaacdf2483298a09bd598740ee0 |
| institution | Directory Open Access Journal |
| issn | 2624-9898 |
| language | English |
| last_indexed | 2024-12-12T23:46:47Z |
| publishDate | 2022-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computer Science |
| spelling | doaj.art-19648eaacdf2483298a09bd598740ee02022-12-22T00:06:49ZengFrontiers Media S.A.Frontiers in Computer Science2624-98982022-03-01410.3389/fcomp.2022.744574744574Modeling Feedback in Interaction With Conversational Agents—A ReviewAgnes Axelsson0Hendrik Buschmeier1Gabriel Skantze2Division of Speech, Music and Hearing (TMH), KTH Royal Institute of Technology, Stockholm, SwedenFaculty of Linguistics and Literary Studies, Bielefeld University, Bielefeld, GermanyDivision of Speech, Music and Hearing (TMH), KTH Royal Institute of Technology, Stockholm, SwedenIntelligent 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.https://www.frontiersin.org/articles/10.3389/fcomp.2022.744574/fullfeedbackgroundingspoken dialoguemultimodal signalshuman-agent interactionreview |
| spellingShingle | Agnes Axelsson Hendrik Buschmeier Gabriel Skantze Modeling Feedback in Interaction With Conversational Agents—A Review Frontiers in Computer Science feedback grounding spoken dialogue multimodal signals human-agent interaction review |
| title | Modeling Feedback in Interaction With Conversational Agents—A Review |
| title_full | Modeling Feedback in Interaction With Conversational Agents—A Review |
| title_fullStr | Modeling Feedback in Interaction With Conversational Agents—A Review |
| title_full_unstemmed | Modeling Feedback in Interaction With Conversational Agents—A Review |
| title_short | Modeling Feedback in Interaction With Conversational Agents—A Review |
| title_sort | modeling feedback in interaction with conversational agents a review |
| topic | feedback grounding spoken dialogue multimodal signals human-agent interaction review |
| url | https://www.frontiersin.org/articles/10.3389/fcomp.2022.744574/full |
| work_keys_str_mv | AT agnesaxelsson modelingfeedbackininteractionwithconversationalagentsareview AT hendrikbuschmeier modelingfeedbackininteractionwithconversationalagentsareview AT gabrielskantze modelingfeedbackininteractionwithconversationalagentsareview |