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 |
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