Multi-level Feature Combination in Dialogue State Tracking

  • Yang ZhengEmail author
  • Ruifang Liu
  • Sheng Gao
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1074)


Dialogue State Tracking is one of the most important component in task-oriented dialog system, which can update the dialogue state and accurately estimate the compact state representation. This paper introduces a multi-level feature combination to capture correlation on the basis of the entire dialog and slots. Based on the Memory-Network [1], which only consider the relevance of current user utterance with historical dialogue context under turn level, we both consider the correlation at the sentence-level and word-level, and give the slot-value pair as input replacing of candidate state pool to estimate the rare slot-value pair. We use Bi-LSTM and self-attention to capture the correlation between internal words from the utterance, the particular slot-value pair and previous unsettled actions, and finally give a confidence degree score to judge whether the particular slot-value pair is the right answer for the current utterance. Our model achieves a good result on the DSTC-2 dataset about 0.74, which is 3% higher than Memory-Network’s 0.71.


Task-oriented dialog system Dialogue state tracking Memory-Network Multi-level feature combination 


  1. 1.
    Perez, J., Liu, F.: Dialog state tracking, a machine reading approach using memory network. arxiv (2017)Google Scholar
  2. 2.
    Yoshino, K., Hiraoka, T., Neubig, G., Nakamura, S.: Dialogue state tracking using long short term memory neural networks. arxiv (2014)Google Scholar
  3. 3.
    Henderson, M., Thomson, B., Young, S.J.: Word-based dialog state tracking with recurrent neural networks. In: Proceedings of SIGDIAL (2014)Google Scholar
  4. 4.
    Mrksic, N., Seaghdha, D.O.S., Wen, T.H.., Thomson, B., Young, S.J.: Neural belief tracker: data-driven dialogue state tracking. In: Proceedings of ACL (2017)Google Scholar
  5. 5.
    Serban, I.V., Sordoni, A., Bengio, Y., Courville, A., Pineau, J.: Building end-to-end dialogue systems using generative hierarchical neural network models. arxiv (2015)Google Scholar
  6. 6.
    Madotto, A., Wu, C., Fung, P.: Mem2Seq: effectively incorporating knowledge bases into end-to-end task-oriented dialog systems. arxiv (2018)Google Scholar
  7. 7.
    Li, X., Chen, Y., Li, L., Gao, J., Celikyilmaz, A.: End-to-end task-completion neural dialogue systems. arxiv (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Beijing University of Posts and TelecommunicationsBeijingChina

Personalised recommendations