Emotional Dialogue Generation Based on Conditional Variational Autoencoder and Dual Emotion Framework

Zhenrong Deng,Hongquan Lin,Wenming Huang,Xiaonan Luo,Rushi Lan,Yaguang Lin

doi:10.1155/2020/8881616

Abstract

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.

Highlights

With the development of privacy protection and incentive technology in the Internet of Things and mobile social networks driven by artificial intelligence, intelligent dialogue systems have entered our daily lives [1,2,3,4]
For the dialogue system based on the Seq2Seq model and the maximum likelihood estimation (MLE) objective, the characteristics of the model determine the general utterance with a greater probability of its tendency to respond, such as “I don’t know” and “Yes.”
The contributions of our work are summarized as follows: (1) We propose a dual-emotional framework for emotional dialogue generation, which comprehensively considers the impact of the emotion of the input sentence and the target emotion on emotional response in order to make our emotional response consistent with the user’s emotion and ensure that the emotional response is controllable

Summary

Introduction

With the development of privacy protection and incentive technology in the Internet of Things and mobile social networks driven by artificial intelligence, intelligent dialogue systems have entered our daily lives [1,2,3,4]. To generate more informative and meaningful responses, much work has been carried out in the open-domain dialogue [11,12,13] These methods focus on the consistency of the conversation content rather on emotion. (1) We propose a dual-emotional framework for emotional dialogue generation, which comprehensively considers the impact of the emotion of the input sentence and the target emotion on emotional response in order to make our emotional response consistent with the user’s emotion and ensure that the emotional response is controllable (2) We combine the conditional variational autoencoder [17] with the dual emotion framework to train an emotional generation system, and experiments prove that our model has strong performance (3) A multiclass emotion classifier based on the BERT [18] model is employed to obtain emotion labels, which improves the accuracy of emotion recognition and emotion expression. We summarize this article and propose directions for the future work in “Conclusion.”

Related Work

Proposed Model

Sequence to Sequence Model Based on the Attention

Experiment

Conclusion