Abstract
Emotional conversation generation model predicts the response according to the current words and the emotional words. However, the researchers only dedicated to adding more emotional words in the conversation generation model to retain the taste of chat users without considering whether the emotion of a response is suitable for human conversations or not. In this paper, we aim to address the issue of emotion drift which indicates the emotion of a response is not the same category as its post in human conversations. We propose a control unit framework, which consists of emotional channels and word-level attention mechanism, to incorporate natural and smooth emotional words into conversation generation. Emotional channel consists six channels, namely like, sadness, disgust, anger, happiness and other ones, which provides strategy choice control unit to generate emotional words. To improve the importance of emotional content, we use the word-level attention mechanism in emotional channel for acquiring a better emotional decoding response. Experimental results suggest that the proposed model is effective not only in generate content but also in emotion.
Highlights
Thanks to the rapid advance of deep learning, neural networks make breakthroughs in speech recognition and machine translation, and expand to the breakthroughs in conversation generation
Emotional controllability is one of the major problems faced by emotional conversation generation
To alleviate the emotion drift, we propose a control unit framework to select the appropriate emotion category for emotional conversation generation
Summary
Thanks to the rapid advance of deep learning, neural networks make breakthroughs in speech recognition and machine translation, and expand to the breakthroughs in conversation generation. The emotional intelligence of conversation generation significantly defines the ability to perceive, understand, express and control emotions [1], developing the methods for conversation generation problems such as semantics, grammar, smoothness, etc. Emotional controllability is one of the major problems faced by emotional conversation generation. The emotion of a response tends to be the same category as the post in human conversations. The control unit, which aims to prevent emotion drift, will be regarded as a vital research issue in the conversation generation for generating emotional responses logically. Many researches have focused on adding emotional characteristics to conversation generation.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
