Learning to balance the coherence and diversity of response generation in generation-based chatbots. (28th August 2020)

• Record Type: Journal Article
• Authors: Wang, Shuliang; Li, Dapeng; Geng, Jing; Yang, Longxing; Leng, Hongyong
• Is Part Of: International journal of advanced robotic systems. Volume 17:Number 4(2020:Jul./Aug.)
• Publication Date: 2020-08-28
• Subjects: Variational autoencoder -- dialog system -- deep learning -- response generation -- chatbots; Robotics -- Periodicals; Robotics; Periodicals; 629.892
• DOI: 10.1177/1729881420953006
• Languages: English
• ISSNs: 1729-8806

Abstract

Generating response with both coherence and diversity is a challenging task in generation-based chatbots. It is more difficult to improve the coherence and diversity of dialog generation at the same time in the response generation model. In this article, we propose an improved method that improves the coherence and diversity of dialog generation by changing the model to use gamma sampling and adding attention mechanism to the knowledge-guided conditional variational autoencoder. The experimental results demonstrate that our proposed method can significantly improve the coherence and diversity of knowledge-guided conditional variational autoencoder for response generation in generation-based chatbots at the same time.