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 | |
会议日期 | 2019 |
会议地点 | Dunhuang |
DOI | 10.1007/978-3-030- 32233-5_1 |
页码 | 3-15 |
英文摘要 | 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. |
会议录出版者 | Technical Committee of Chinese Information, China Computer Federation |
会议录出版地 | Dunhuang |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48870] ![]() |
专题 | 模式识别国家重点实验室_自然语言处理 |
作者单位 | 1.中国科学院大学人工智能学院 2.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]. 见:. Dunhuang. 2019. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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