In-Context Learning for Few-Shot Dialogue State Tracking
This work addresses the challenge of data scarcity for dialogue state tracking, benefiting developers of task-oriented dialogue systems by reducing annotation costs, though it is incremental as it builds on existing in-context learning methods.
The paper tackles the problem of costly annotation for dialogue state tracking by proposing an in-context learning framework that uses a pre-trained language model to decode dialogue states without fine-tuning, achieving substantial performance gains over previous state-of-the-art models in few-shot and zero-shot settings on the MultiWOZ dataset.
Collecting and annotating task-oriented dialogues is time-consuming and costly; thus, zero and few shot learning could greatly benefit dialogue state tracking (DST). In this work, we propose an in-context learning (ICL) framework for zero-shot and few-shot learning DST, where a large pre-trained language model (LM) takes a test instance and a few exemplars as input, and directly decodes the dialogue state without any parameter updates. To better leverage a tabular domain description in the LM prompt, we reformulate DST into a text-to-SQL problem. We also propose a novel approach to retrieve annotated dialogues as exemplars. Empirical results on MultiWOZ show that our method IC-DST substantially outperforms previous fine-tuned state-of-the-art models in few-shot settings. In addition, we test IC-DST in zero-shot settings, in which the model only takes a fixed task instruction as input, finding that it outperforms previous zero-shot methods by a large margin.