Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks


  • Lu Chen Shanghai Jiao Tong University
  • Boer Lv Shanghai Jiao Tong University
  • Chi Wang Shanghai Jiao Tong University
  • Su Zhu Shanghai Jiao Tong University
  • Bowen Tan Shanghai Jiao Tong University
  • Kai Yu Shanghai Jiao Tong University



Dialogue state tracking (DST) aims at estimating the current dialogue state given all the preceding conversation. For multi-domain DST, the data sparsity problem is also a major obstacle due to the increased number of state candidates. Existing approaches generally predict the value for each slot independently and do not consider slot relations, which may aggravate the data sparsity problem. In this paper, we propose a Schema-guided multi-domain dialogue State Tracker with graph attention networks (SST) that predicts dialogue states from dialogue utterances and schema graphs which contain slot relations in edges. We also introduce a graph attention matching network to fuse information from utterances and graphs, and a recurrent graph attention network to control state updating. Experiment results show that our approach obtains new state-of-the-art performance on both MultiWOZ 2.0 and MultiWOZ 2.1 benchmarks.




How to Cite

Chen, L., Lv, B., Wang, C., Zhu, S., Tan, B., & Yu, K. (2020). Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 7521-7528.



AAAI Technical Track: Natural Language Processing