Fully Statistical Neural Belief Tracking

Nikola Mrkšić, Ivan Vulić


Abstract
This paper proposes an improvement to the existing data-driven Neural Belief Tracking (NBT) framework for Dialogue State Tracking (DST). The existing NBT model uses a hand-crafted belief state update mechanism which involves an expensive manual retuning step whenever the model is deployed to a new dialogue domain. We show that this update mechanism can be learned jointly with the semantic decoding and context modelling parts of the NBT model, eliminating the last rule-based module from this DST framework. We propose two different statistical update mechanisms and show that dialogue dynamics can be modelled with a very small number of additional model parameters. In our DST evaluation over three languages, we show that this model achieves competitive performance and provides a robust framework for building resource-light DST models.
Anthology ID:
P18-2018
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
108–113
Language:
URL:
https://aclanthology.org/P18-2018
DOI:
10.18653/v1/P18-2018
Bibkey:
Cite (ACL):
Nikola Mrkšić and Ivan Vulić. 2018. Fully Statistical Neural Belief Tracking. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 108–113, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Fully Statistical Neural Belief Tracking (Mrkšić & Vulić, ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-2018.pdf
Code
 nmrksic/neural-belief-tracker