RefNet: A Reference-Aware Network for Background Based Conversation


  • Chuan Meng Shandong University
  • Pengjie Ren University of Amsterdam
  • Zhumin Chen Shandong University
  • Christof Monz University of Amsterdam
  • Jun Ma Shandong University
  • Maarten de Rijke University of Amsterdam



Existing conversational systems tend to generate generic responses. Recently, Background Based Conversation (BBCs) have been introduced to address this issue. Here, the generated responses are grounded in some background information. The proposed methods for BBCs are able to generate more informative responses, however, they either cannot generate natural responses or have difficulties in locating the right background information. In this paper, we propose a Reference-aware Network (RefNet) to address both issues. Unlike existing methods that generate responses token by token, RefNet incorporates a novel reference decoder that provides an alternative way to learn to directly select a semantic unit (e.g., a span containing complete semantic information) from the background. Experimental results show that RefNet significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, indicating that RefNet can generate more appropriate and human-like responses.




How to Cite

Meng, C., Ren, P., Chen, Z., Monz, C., Ma, J., & de Rijke, M. (2020). RefNet: A Reference-Aware Network for Background Based Conversation. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 8496-8503.



AAAI Technical Track: Natural Language Processing