Fully Statistical Neural Belief Tracking
This work addresses the need for more automated and resource-light dialogue state tracking models, though it is incremental as it builds on an existing framework.
The paper tackles the problem of manual retuning in Neural Belief Tracking for Dialogue State Tracking by learning the belief state update mechanism jointly with other model components, eliminating the last rule-based module. It shows competitive performance across three languages with a small number of additional parameters.
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.