SF-DST: Few-Shot Self-Feeding Reading Comprehension Dialogue State Tracking with Auxiliary Task
Jihyun Lee, Gary Geunbae Lee · Interspeech 2022 · 2022
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 selffeeding 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.