Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation
Chen, Xiuyi1,2,3; Meng, Fandong4; Li, Peng4; Chen, Feilong1,2,3; Xu, Shuang1; Xu, Bo1,2,3; Zhou, Jie4
2020-11
会议名称Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
会议日期2020-11
会议地点online
摘要

Knowledge selection plays an important role in knowledge-grounded dialogue, which is a challenging task to generate more informative responses by leveraging external knowledge. Recently, latent variable models have been proposed to deal with the diversity of knowledge selection by using both prior and posterior distributions over knowledge and achieve promising performance. However, these models suffer from a huge gap between prior and posterior knowledge selection. Firstly, the prior selection module may not learn to select knowledge properly because of lacking the necessary posterior information. Secondly, latent variable models suffer from the exposure bias that dialogue generation is based on the knowledge selected from the posterior distribution at training but from the prior distribution at inference. Here, we deal with these issues on two aspects: (1) We enhance the prior selection module with the necessary posterior information obtained from the specially designed Posterior Information Prediction Module (PIPM); (2) We propose a Knowledge Distillation Based Training Strategy (KDBTS) to train the decoder with the knowledge selected from the prior distribution, removing the exposure bias of knowledge selection. Experimental results on two knowledge-grounded dialogue datasets show that both PIPM and KDBTS achieve performance improvement over the state-of-the-art latent variable model and their combination shows further improvement.

收录类别EI
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/48919
专题数字内容技术与服务研究中心_听觉模型与认知计算
数字内容技术与服务研究中心
作者单位1.Institute of Automation, Chinese Academy of Sciences (CASIA). Beijing, China
2.Research Center for Brain-inspired Intelligence, CASIA
3.University of Chinese Academy of Sciences, Beijing, China
4.Pattern Recognition Center, WeChat AI, Tencent Inc, Beijing, China
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
Chen, Xiuyi,Meng, Fandong,Li, Peng,et al. Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation[C],2020.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
2212_Paper.pdf(389KB)会议论文 开放获取CC BY-NC-SA浏览
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Chen, Xiuyi]的文章
[Meng, Fandong]的文章
[Li, Peng]的文章
百度学术
百度学术中相似的文章
[Chen, Xiuyi]的文章
[Meng, Fandong]的文章
[Li, Peng]的文章
必应学术
必应学术中相似的文章
[Chen, Xiuyi]的文章
[Meng, Fandong]的文章
[Li, Peng]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 2212_Paper.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。