KC2UM: Knowledge-Conversation Cyclic Utilization Mechanism for Knowledge-Grounded Dialogue Generation

Yajing Sun, Yue Hu, Luxi Xing, Wei Peng, Yuqiang Xie, Xingsheng ZhangIJCNN 2022 · OpenReview

Abstract

End-to-End open-domain dialogue systems suffer from the issues of generating inconsistent and repetitive responses. Existing dialogue models pay attention to unilaterally incorporating personalized knowledge into the dialogue to enhance the quality of generated response. However, they ignore that incorporating the personality-related information from dialogue history into personalized knowledge can boost the subsequent dialogue quality. In this paper, A Knowledge-Conversation Cyclic Utilization Mechanism (KC2UM) is proposed to enhance the dialogue quality. Specifically, A novel cyclic interaction module is designed to iteratively incorporate personalized knowledge into each turn conversation and capture the personality-related conversation information to enhance personalized knowledge semantic representation. We represent the knowledge with semantic and utilization representations to keep track of the personalized knowledge utilization. Experiments on two knowledge-grounded dialogue datasets show that our approach manages to select knowledge more accurately and generates more informative responses.
BibTeX
@inproceedings{sun2022kc,
  author = {Yajing Sun and Yue Hu and Luxi Xing and Wei Peng and Yuqiang Xie and Xingsheng Zhang},
  title = {{KC2UM: Knowledge-Conversation Cyclic Utilization Mechanism for Knowledge-Grounded Dialogue Generation}},
  booktitle = {IJCNN},
  year = {2022},
  url = {https://openreview.net/forum?id=uJobSJXKql},
}
Figure