Topic-extended Emotional Conversation Generation Model Based on Joint Decoding
The research on the expression of emotion in human-computer dialogue can greatly improve the user experience. Existing research has paid a lot of attention to how to generate specific emotional content and how to improve the extraction rate of emotions, while ignoring the reduction of emotion expres...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9459747/ |
| _version_ | 1818479990332719104 |
|---|---|
| author | Mengshi Duan Qing Li Le Xiao |
| author_facet | Mengshi Duan Qing Li Le Xiao |
| author_sort | Mengshi Duan |
| collection | DOAJ |
| description | The research on the expression of emotion in human-computer dialogue can greatly improve the user experience. Existing research has paid a lot of attention to how to generate specific emotional content and how to improve the extraction rate of emotions, while ignoring the reduction of emotion expression caused by factors such as topics and emotions added to the encoder. This paper proposes a novel Topic-extended Emotional Conversation Generation Model Based on Joint Decoding (TECM-JD). The model embeds the specified emotion category as an additional input into the emotional independent unit of the decoder, in order to reduce the expression of the content affected by adding emotion into the model. The joint attention mechanism is used to obtain the input sequence content and the input sequence topic word content obtained by the Twitter LDA model, which ensures that the output topic and the input are under the same topic. The experimental results show that the proposed model can generate richer emotional content related to the topic and have good performance and are superior to traditional dialogue models. |
| first_indexed | 2024-12-10T11:17:09Z |
| format | Article |
| id | doaj.art-0b68ad760bff433fb9ff7ffac8912da8 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-10T11:17:09Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-0b68ad760bff433fb9ff7ffac8912da82022-12-22T01:51:06ZengIEEEIEEE Access2169-35362021-01-019899348994010.1109/ACCESS.2021.30904359459747Topic-extended Emotional Conversation Generation Model Based on Joint DecodingMengshi Duan0https://orcid.org/0000-0002-7066-4289Qing Li1Le Xiao2Henan University of Technology, Zhengzhou, ChinaHenan University of Technology, Zhengzhou, ChinaKey Laboratory of Grain Information Processing and Control, Ministry of Education, Henan University of Technology, Zhengzhou, ChinaThe research on the expression of emotion in human-computer dialogue can greatly improve the user experience. Existing research has paid a lot of attention to how to generate specific emotional content and how to improve the extraction rate of emotions, while ignoring the reduction of emotion expression caused by factors such as topics and emotions added to the encoder. This paper proposes a novel Topic-extended Emotional Conversation Generation Model Based on Joint Decoding (TECM-JD). The model embeds the specified emotion category as an additional input into the emotional independent unit of the decoder, in order to reduce the expression of the content affected by adding emotion into the model. The joint attention mechanism is used to obtain the input sequence content and the input sequence topic word content obtained by the Twitter LDA model, which ensures that the output topic and the input are under the same topic. The experimental results show that the proposed model can generate richer emotional content related to the topic and have good performance and are superior to traditional dialogue models.https://ieeexplore.ieee.org/document/9459747/Dialogue generation modeltopic expansionjoint attention mechanismjoint decoder |
| spellingShingle | Mengshi Duan Qing Li Le Xiao Topic-extended Emotional Conversation Generation Model Based on Joint Decoding IEEE Access Dialogue generation model topic expansion joint attention mechanism joint decoder |
| title | Topic-extended Emotional Conversation Generation Model Based on Joint Decoding |
| title_full | Topic-extended Emotional Conversation Generation Model Based on Joint Decoding |
| title_fullStr | Topic-extended Emotional Conversation Generation Model Based on Joint Decoding |
| title_full_unstemmed | Topic-extended Emotional Conversation Generation Model Based on Joint Decoding |
| title_short | Topic-extended Emotional Conversation Generation Model Based on Joint Decoding |
| title_sort | topic extended emotional conversation generation model based on joint decoding |
| topic | Dialogue generation model topic expansion joint attention mechanism joint decoder |
| url | https://ieeexplore.ieee.org/document/9459747/ |
| work_keys_str_mv | AT mengshiduan topicextendedemotionalconversationgenerationmodelbasedonjointdecoding AT qingli topicextendedemotionalconversationgenerationmodelbasedonjointdecoding AT lexiao topicextendedemotionalconversationgenerationmodelbasedonjointdecoding |