84 citations · 86 across the 3 of their papers we have counts for
3 papers
cs.CL2020★ 1 cited
StyleDGPT: Stylized Response Generation with Pre-trained Language Models
Ze Yang, Wei Wu, Can Xu +5
Generating responses following a desired style has great potentials to extend applications of open-domain dialogue systems, yet is refrained by lacking of parallel data for trainin…
cs.CL2020★ 84 cited
Low-Resource Knowledge-Grounded Dialogue Generation
Xueliang Zhao, Wei Wu, Chongyang Tao +3
Responding with knowledge has been recognized as an important capability for an intelligent conversational agent. Yet knowledge-grounded dialogues, as training data for learning su…
cs.CL2019★ 1 cited
Read, Attend and Comment: A Deep Architecture for Automatic News Comment Generation
Ze Yang, Can Xu, Wei Wu +1
Automatic news comment generation is a new testbed for techniques of natural language generation. In this paper, we propose a "read-attend-comment" procedure for news comment gener…