Multi-Domain Spoken Language Understanding Using Domain- and Task-Aware Parameterization
This work addresses the scalability and cost issues in annotating data for spoken language understanding across multiple domains, offering an incremental improvement over existing multi-domain learning methods.
The paper tackles the problem of multi-domain spoken language understanding by proposing a model with domain- and task-specific parameters to improve knowledge transfer across domains, achieving the best results on 5 domains and outperforming prior models by 12.4% when adapting to a new domain with limited data.
Spoken language understanding has been addressed as a supervised learning problem, where a set of training data is available for each domain. However, annotating data for each domain is both financially costly and non-scalable so we should fully utilize information across all domains. One existing approach solves the problem by conducting multi-domain learning, using shared parameters for joint training across domains. We propose to improve the parameterization of this method by using domain-specific and task-specific model parameters to improve knowledge learning and transfer. Experiments on 5 domains show that our model is more effective for multi-domain SLU and obtain the best results. In addition, we show its transferability by outperforming the prior best model by 12.4\% when adapting to a new domain with little data.