Emotional Dialogue Generation Based on Conditional Variational Autoencoder and Dual Emotion Framework
Joint Authors
Lan, Rushi
Luo, Xiaonan
Deng, Zhenrong
Lin, Hongquan
Huang, Wenming
Source
Wireless Communications and Mobile Computing
Issue
Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-10, 10 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2020-12-28
Country of Publication
Egypt
No. of Pages
10
Main Subjects
Information Technology and Computer Science
Abstract EN
An excellent dialogue system needs to not only generate rich and diverse logical responses but also meet the needs of users for emotional communication.
However, despite much work, these two problems have not been solved.
In this paper, we propose a model based on conditional variational autoencoder and dual emotion framework (CVAE-DE) to generate emotional responses.
In our model, latent variables of the conditional variational autoencoder are adopted to promote the diversity of conversation.
A dual emotion framework is adopted to control the explicit emotion of the response and prevent the conversation from generating emotion drift indicating that the emotion of the response is not related to the input sentence.
A multiclass emotion classifier based on the Bidirectional Encoder Representations from Transformers (BERT) model is employed to obtain emotion labels, which promotes the accuracy of emotion recognition and emotion expression.
A large number of experiments show that our model not only generates rich and diverse responses but also is emotionally coherent and controllable.
American Psychological Association (APA)
Deng, Zhenrong& Lin, Hongquan& Huang, Wenming& Lan, Rushi& Luo, Xiaonan. 2020. Emotional Dialogue Generation Based on Conditional Variational Autoencoder and Dual Emotion Framework. Wireless Communications and Mobile Computing،Vol. 2020, no. 2020, pp.1-10.
https://search.emarefa.net/detail/BIM-1214858
Modern Language Association (MLA)
Deng, Zhenrong…[et al.]. Emotional Dialogue Generation Based on Conditional Variational Autoencoder and Dual Emotion Framework. Wireless Communications and Mobile Computing No. 2020 (2020), pp.1-10.
https://search.emarefa.net/detail/BIM-1214858
American Medical Association (AMA)
Deng, Zhenrong& Lin, Hongquan& Huang, Wenming& Lan, Rushi& Luo, Xiaonan. Emotional Dialogue Generation Based on Conditional Variational Autoencoder and Dual Emotion Framework. Wireless Communications and Mobile Computing. 2020. Vol. 2020, no. 2020, pp.1-10.
https://search.emarefa.net/detail/BIM-1214858
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1214858