A Control Unit for Emotional Conversation Generation
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...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9020093/ |
_version_ | 1818732794954645504 |
---|---|
author | Zhiqiang Ma Rui Yang Baoxiang Du Yan Chen |
author_facet | Zhiqiang Ma Rui Yang Baoxiang Du Yan Chen |
author_sort | Zhiqiang Ma |
collection | DOAJ |
description | 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. |
first_indexed | 2024-12-17T23:39:14Z |
format | Article |
id | doaj.art-433b3315a12d4c4fb313b72b30efab4c |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-12-17T23:39:14Z |
publishDate | 2020-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-433b3315a12d4c4fb313b72b30efab4c2022-12-21T21:28:28ZengIEEEIEEE Access2169-35362020-01-018431684317610.1109/ACCESS.2020.29776979020093A Control Unit for Emotional Conversation GenerationZhiqiang Ma0https://orcid.org/0000-0002-5554-2857Rui Yang1https://orcid.org/0000-0002-7733-0636Baoxiang Du2https://orcid.org/0000-0003-4709-4385Yan Chen3https://orcid.org/0000-0003-0279-2366College of Data Science and Application, Inner Mongolia University of Technology, Hohhot, ChinaCollege of Data Science and Application, Inner Mongolia University of Technology, Hohhot, ChinaCollege of Data Science and Application, Inner Mongolia University of Technology, Hohhot, ChinaCollege of Data Science and Application, Inner Mongolia University of Technology, Hohhot, ChinaEmotional 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.https://ieeexplore.ieee.org/document/9020093/Control unitparallel channelcontrol unit-based frameworkemotional control conversation model |
spellingShingle | Zhiqiang Ma Rui Yang Baoxiang Du Yan Chen A Control Unit for Emotional Conversation Generation IEEE Access Control unit parallel channel control unit-based framework emotional control conversation model |
title | A Control Unit for Emotional Conversation Generation |
title_full | A Control Unit for Emotional Conversation Generation |
title_fullStr | A Control Unit for Emotional Conversation Generation |
title_full_unstemmed | A Control Unit for Emotional Conversation Generation |
title_short | A Control Unit for Emotional Conversation Generation |
title_sort | control unit for emotional conversation generation |
topic | Control unit parallel channel control unit-based framework emotional control conversation model |
url | https://ieeexplore.ieee.org/document/9020093/ |
work_keys_str_mv | AT zhiqiangma acontrolunitforemotionalconversationgeneration AT ruiyang acontrolunitforemotionalconversationgeneration AT baoxiangdu acontrolunitforemotionalconversationgeneration AT yanchen acontrolunitforemotionalconversationgeneration AT zhiqiangma controlunitforemotionalconversationgeneration AT ruiyang controlunitforemotionalconversationgeneration AT baoxiangdu controlunitforemotionalconversationgeneration AT yanchen controlunitforemotionalconversationgeneration |