Goal-Oriented Multi-Task BERT-Based Dialogue State Tracker
This work addresses the scalability challenge for virtual assistants like Alexa or Siri by enabling them to handle unseen services, though it is incremental as it builds on existing BERT and reading comprehension architectures.
The paper tackles the problem of zero-shot dialogue state tracking for unseen services in virtual assistants, proposing a BERT-based model that achieves a joint goal accuracy of 53.97% on the Schema-Guided Dialogue dataset, outperforming the baseline.
Dialogue State Tracking (DST) is a core component of virtual assistants such as Alexa or Siri. To accomplish various tasks, these assistants need to support an increasing number of services and APIs. The Schema-Guided State Tracking track of the 8th Dialogue System Technology Challenge highlighted the DST problem for unseen services. The organizers introduced the Schema-Guided Dialogue (SGD) dataset with multi-domain conversations and released a zero-shot dialogue state tracking model. In this work, we propose a GOaL-Oriented Multi-task BERT-based dialogue state tracker (GOLOMB) inspired by architectures for reading comprehension question answering systems. The model "queries" dialogue history with descriptions of slots and services as well as possible values of slots. This allows to transfer slot values in multi-domain dialogues and have a capability to scale to unseen slot types. Our model achieves a joint goal accuracy of 53.97% on the SGD dataset, outperforming the baseline model.