Knowledge Commons of Institute of Automation,CAS
Variational Attention for Commonsense Knowledge Aware Conversation Generation | |
Bai GR(白桂荣)1,2; He SZ(何世柱)1,2; Liu K(刘康)1,2; Zhao J(赵军)1,2 | |
2019 | |
会议名称 | NLPCC2019 |
页码 | 3-15 |
会议日期 | 2019 |
会议地点 | Dunhuang |
出版地 | Dunhuang |
出版者 | Technical Committee of Chinese Information, China Computer Federation |
摘要 | Conversation generation is an important task in natural language processing, and commonsense knowledge is vital to provide a shared background for better replying. In this paper, we present a novel commonsense knowledge aware conversation generation model, which adopts variational attention for incorporating commonsense knowledge to generate more appropriate conversation. Given a post, the model retrieves relevant knowledge graphs from a knowledge base, and then attentively incorporates knowledge to its response. For enhancing attention to incorporate more clean and suitable knowledge into response generation, we adopt variational attention rather than standard neural attention on knowledge graphs, which is unlike previous knowledge aware generation models. Experimental results show that the variational attention based model can incorporate more clean and suitable knowledge into response generation. |
DOI | 10.1007/978-3-030- 32233-5_1 |
语种 | 英语 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48870 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学人工智能学院 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Bai GR,He SZ,Liu K,et al. Variational Attention for Commonsense Knowledge Aware Conversation Generation[C]. Dunhuang:Technical Committee of Chinese Information, China Computer Federation,2019:3-15. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
NLPCC.pdf(322KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论