Teacher-Student Framework Enhanced Multi-domain Dialogue Generation
This addresses a key bottleneck in task-oriented dialogue systems for multi-domain applications, though it appears incremental as it builds on existing teacher-student methods.
The paper tackles the problem of error propagation in state trackers for multi-domain dialogue systems by proposing a teacher-student framework that eliminates the need for external trackers while leveraging labeled data. Experiments show the system outperforms one using a belief tracker.
Dialogue systems dealing with multi-domain tasks are highly required. How to record the state remains a key problem in a task-oriented dialogue system. Normally we use human-defined features as dialogue states and apply a state tracker to extract these features. However, the performance of such a system is limited by the error propagation of a state tracker. In this paper, we propose a dialogue generation model that needs no external state trackers and still benefits from human-labeled semantic data. By using a teacher-student framework, several teacher models are firstly trained in their individual domains, learn dialogue policies from labeled states. And then the learned knowledge and experience are merged and transferred to a universal student model, which takes raw utterance as its input. Experiments show that the dialogue system trained under our framework outperforms the one uses a belief tracker.