2018

Toward Scalable Neural Dialogue State Tracking Model

Nouri, Elnaz, Hosseini-Asl, Ehsan

Understand

The latency in the current neural based dialogue state tracking models prohibits them from being used efficiently for deployment in production systems, albeit their highly accurate performance.

  • This paper proposes a new scalable and accurate neural dialogue state tracking model, based on the recently proposed Global-Local Self-Attention encoder (GLAD) model by Zhong et al.
  • which uses global modules to share parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features.
  • By using only one recurrent networks with global conditioning, compared to (1 + \# slots) recurrent networks with global and local conditioning used in the GLAD model, our proposed model reduces the latency in training and inference times by $35\%$ on average, while preserving performance of belief state tracking, by $97.38\%$ on turn request and $88.51\%$ on joint goal and accuracy.

Built on

  • Long short-term memory

    S. Hochreiter and J. Schmidhuber · 1997

    Earlier work this paper cites.

  • The dialog state tracking challenge

    J. D. Williams, A. Raux, D. Ramachandran, and A. W. Black · 2013

    Earlier work this paper cites.

  • Glove: Global vectors for word representation

    J. Pennington, R. Socher, and C. Manning · 2014

    Earlier work this paper cites.

  • A joint many-task model: Growing a neural network for multiple nlp tasks

    K. Hashimoto, C. Xiong, Y. Tsuruoka, and R. Socher · 2017

    Earlier work this paper cites.

Similar

  • Neural belief tracker: Data-driven dialogue state tracking

    N. Mrksic, D. Ó. Séaghdha, T.-H. Wen, B. Thomson, and S. J. Young · 2017

    Cited alongside, same era.

  • Scalable multi-domain dialogue state tracking

    A. Rastogi, D. Z. Hakkani-Tür, and L. P. Heck · 2017

    Cited alongside, same era.

  • A network-based end-to-end trainable task-oriented dialogue system

    T.-H. Wen, L. M. Rojas-Barahona, M. Gasic, N. Mrksic, P. hao Su, S. Ultes, , S. J. Young, and D. Vandyke · 2017

    Cited alongside, same era.

Then

  • Multiwoz - a large-scale multi-domain wizard-of-oz dataset for task-oriented dialogue modelling

    P. Budzianowski, T.-H. Wen, B.-H. Tseng, I. Casanueva, S. Ultes, O. Ramadan, and M. Gavsi’c · 2018

    Closest in time.

  • An end-to-end approach for handling unknown slot values in dialogue state tracking

    P. Xu and Q. Hu · 2018

    Closest in time.

  • Global-locally self-attentive dialogue state tracker

    V. Zhong, C. Xiong, and R. Socher · 2018

    Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…