16/11/2020

Knowledge-Grounded Dialogue Generation with Pre-trained Language Models

Xueliang Zhao, Wei Wu, Can Xu, Chongyang Tao, Dongyan Zhao, Rui Yan

Keywords: knowledge-grounded generation, equipping, knowledge selection, response generation

Abstract Paper Similar Papers

Abstract: We study knowledge-grounded dialogue generation with pre-trained language models. To leverage the redundant external knowledge under capacity constraint, we propose equipping response generation defined by a pre-trained language model with a knowledge selection module, and an unsupervised approach to jointly optimizing knowledge selection and response generation with unlabeled dialogues. Empirical results on two benchmarks indicate that our model can significantly outperform state-of-the-art methods in both automatic evaluation and human judgment.

 0
 0
 0
 1
  Share    
This is an embedded video. Talk and the respective paper are published at EMNLP 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 8:08 
 0
 0
 0
 1
 16:40 
 0
 0
 0
 0
 11:13 
 0
 0
 0
 0
 11:43 
 1
 0
 0
 0
 11:29 
 0
 0
 0
 0
 14:48 
 0
 0
 0
 1
 3:22 
 0
 0
 0
 1
 10:26 
 0
 0
 0
 0
 18:11 
 0
 0
 0
 1
 10:45 
 0
 0
 0
 0
 9:58 
 0
 0
 0
 1
 10:01 
 0
 0
 0
 0
 6:54 
 0
 0
 0
 0
 14:42 
 0
 0
 0
 0
 14:43 
 0
 0
 0
 0
 3:28 
 0
 0
 0
 1
 11:14 
 0
 0
 0
 0
 15:37 
 0
 0
 0
 0
 4:52 
 0
 0
 0
 0
 11:22 
 0
 0
 0
 0
 11:37 
 0
 0
 0
 0
 6:58 
 0
 0
 0
 0
 15:03 
 0
 0
 0
 0
 16:13 
 0
 0
 0
 0
 12:00 
 0
 0
 0
 0
 13:17 
 0
 0
 0
 0
 10:27 
 0
 0
 0
 0
 14:44 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 12:35 
 0
 0
 0
 0
 18:24 
 0
 0
 0
 0
 13:42 
 0
 0
 0
 0
 10:13 
 0
 0
 0
 0
 15:28 
 0
 0
 0
 0
 12:23 
 0
 0
 0
 0
 11:42 
 0
 0
 0
 0
 10:57 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 15:12 
 0
 0
 0
 0
 3:22