SF-DST: Few-Shot Self-Feeding Reading Comprehension Dialogue State Tracking with Auxiliary Task
This work addresses the problem of tracking user requests in dialogues with limited data, which is incremental as it builds on existing few-shot DST methods.
The paper tackled few-shot dialogue state tracking by introducing a self-feeding belief state input and a slot-gate auxiliary task, achieving the best score in a few-shot setting on multiWOZ 2.0 across four domains.
Few-shot dialogue state tracking (DST) model tracks user requests in dialogue with reliable accuracy even with a small amount of data. In this paper, we introduce an ontology-free few-shot DST with self-feeding belief state input. The self-feeding belief state input increases the accuracy in multi-turn dialogue by summarizing previous dialogue. Also, we newly developed a slot-gate auxiliary task. This new auxiliary task helps classify whether a slot is mentioned in the dialogue. Our model achieved the best score in a few-shot setting for four domains on multiWOZ 2.0.