Multi-domain Dialog State Tracking using Recurrent Neural Networks
This addresses the challenge of building scalable dialog systems for various domains, but it is incremental as it extends existing methods to multi-domain settings.
The paper tackled the problem of dialog state tracking across multiple domains by training a general model that outperforms domain-specific ones, showing improvements regardless of in-domain data availability.
Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, well-defined domain in mind. This paper shows that dialog data drawn from different dialog domains can be used to train a general belief tracking model which can operate across all of these domains, exhibiting superior performance to each of the domain-specific models. We propose a training procedure which uses out-of-domain data to initialise belief tracking models for entirely new domains. This procedure leads to improvements in belief tracking performance regardless of the amount of in-domain data available for training the model.