Chinese Emotional Dialogue Response Generation via Reinforcement Learning
العنوان: | Chinese Emotional Dialogue Response Generation via Reinforcement Learning |
---|---|
المؤلفون: | Zhenrong Deng, Xiyan Sun, Wenming Huang, Xiaonan Luo, Jing Wang, Zhuo Chen, Rushi Lan |
المصدر: | ACM Transactions on Internet Technology. 21:1-17 |
بيانات النشر: | Association for Computing Machinery (ACM), 2021. |
سنة النشر: | 2021 |
مصطلحات موضوعية: | Computer Networks and Communications, Process (engineering), Computer science, business.industry, media_common.quotation_subject, Emotion classification, 020206 networking & telecommunications, 02 engineering and technology, computer.software_genre, Expression (mathematics), 0202 electrical engineering, electronic engineering, information engineering, Beam search, Reinforcement learning, 020201 artificial intelligence & image processing, Quality (business), Artificial intelligence, Function (engineering), business, computer, Decoding methods, Natural language processing, media_common |
الوصف: | In an open-domain dialogue system, recognition and expression of emotions are the key factors for success. Most of the existing research related to Chinese dialogue systems aims at improving the quality of content but ignores the expression of human emotions. In this article, we propose a Chinese emotional dialogue response generation algorithm based on reinforcement learning that can generate responses not only according to content but also according to emotion. In the proposed method, a multi-emotion classification model is first used to add emotion labels to the corpus of post-response pairs. Then, with the help of reinforcement learning, the reward function is constructed based on two aspects, namely, emotion and content. Among the generated candidates, the system selects the one with long-term success as the best reply. At the same time, to avoid safe responses and diversify dialogue, a diversity beam search algorithm is applied in the decoding process. The comparative experiments demonstrate that the proposed model achieves satisfactory results according to both automatic and human evaluations. |
تدمد: | 1557-6051 1533-5399 |
URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_________::261029bd2c3facf3c83336430770c49a https://doi.org/10.1145/3446390 |
رقم الأكسشن: | edsair.doi...........261029bd2c3facf3c83336430770c49a |
قاعدة البيانات: | OpenAIRE |
تدمد: | 15576051 15335399 |
---|