Learning to Copy Coherent Knowledge for Response Generation

Authors

  • Jiaqi Bai School of Cyber Science and Technology, Beihang University, Beijing, China
  • Ze Yang State Key Lab of Software Development Environment, Beihang University, Beijing, China
  • Xinnian Liang State Key Lab of Software Development Environment, Beihang University, Beijing, China
  • Wei Wang China Resources Group, Shenzhen, China
  • Zhoujun Li School of Cyber Science and Technology, Beihang University, Beijing, China State Key Lab of Software Development Environment, Beihang University, Beijing, China

Keywords:

Conversational AI/Dialog Systems

Abstract

Knowledge-driven dialog has shown remarkable performance to alleviate the problem of generating uninformative responses in the dialog system. However, incorporating knowledge coherently and accurately into response generation is still far from being solved. Previous works dropped into the paradigm of non-goal-oriented knowledge-driven dialog, they are prone to ignore the effect of dialog goal, which has potential impacts on knowledge exploitation and response generation. To address this problem, this paper proposes a Goal-Oriented Knowledge Copy network, GOKC. Specifically, a goal-oriented knowledge discernment mechanism is designed to help the model discern the knowledge facts that are highly correlated to the dialog goal and the dialog context. Besides, a context manager is devised to copy facts not only from the discerned knowledge but also from the dialog goal and the dialog context, which allows the model to accurately restate the facts in the generated response. The empirical studies are conducted on two benchmarks of goal-oriented knowledge-driven dialog generation. The results show that our model can significantly outperform several state-of-the-art models in terms of both automatic evaluation and human judgments.

Downloads

Published

2021-05-18

How to Cite

Bai, J., Yang, Z., Liang, X., Wang, W., & Li, Z. (2021). Learning to Copy Coherent Knowledge for Response Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14), 12535-12543. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17486

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing I