Learning to balance the coherence and diversity of response generation in generation-based chatbots
文献类型：期刊论文
| 作者 | Wang, Shuliang1,2; Li, Dapeng1; Geng, Jing1,2; Yang, Longxing3; Leng, Hongyong1 |
| 刊名 | INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS
 |
| 出版日期 | 2020-07-01 |
| 卷号 | 17期号:4页码:11 |
| 关键词 | Variational autoencoder dialog system deep learning response generation chatbots |
| ISSN号 | 1729-8814 |
| DOI | 10.1177/1729881420953006 |
| 英文摘要 | 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. |
| 资助项目 | Beijing Municipal Science and Technology Project[Z171100005117002] ; Open Fund of Key Laboratory for National Geographic Census and Monitoring, National Administration of Surveying, Mapping and Geoformation[2017NGCMZD03] |
| WOS研究方向 | Robotics |
| 语种 | 英语 |
| WOS记录号 | WOS:000567168500001 |
| 出版者 | SAGE PUBLICATIONS INC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/15502]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Li, Dapeng; Geng, Jing |
| 作者单位 | 1.Beijing Inst Technol, Sch Comp Sci & Technol, 5 South St, Beijing 100081, Peoples R China 2.Beijing Inst Technol, Acad E Govt, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Shuliang,Li, Dapeng,Geng, Jing,et al. Learning to balance the coherence and diversity of response generation in generation-based chatbots[J]. INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS,2020,17(4):11. |
| APA | Wang, Shuliang,Li, Dapeng,Geng, Jing,Yang, Longxing,&Leng, Hongyong.(2020).Learning to balance the coherence and diversity of response generation in generation-based chatbots.INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS,17(4),11. |
| MLA | Wang, Shuliang,et al."Learning to balance the coherence and diversity of response generation in generation-based chatbots".INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS 17.4(2020):11. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。