Google Assistant

BERT-based candidate-attended dialogue state tracking with zero-shot generalization

A preprint introduces a scalable multi-domain dialogue state tracking (DST) framework that uses pretrained BERT to achieve zero-shot generalization across domains without additional training. The system is evaluated on the Schema-Guided Dialogue (SGD) dataset, showing improvement over prior baselines. The work targets scalability challenges in task-oriented dialogue systems like voice assistants.