Intent-driven In-context Learning for Few-shot Dialogue State Tracking
This addresses the problem of expensive and noisy DST data for task-oriented dialogue systems, offering an incremental improvement with specific gains.
The paper tackles the challenges of implicit information and noise in dialogue state tracking (DST) by introducing IDIC-DST, which uses intent-driven in-context learning to augment dialogue information and retrieve examples, achieving state-of-the-art performance in few-shot settings on MultiWOZ datasets.
Dialogue state tracking (DST) plays an essential role in task-oriented dialogue systems. However, user's input may contain implicit information, posing significant challenges for DST tasks. Additionally, DST data includes complex information, which not only contains a large amount of noise unrelated to the current turn, but also makes constructing DST datasets expensive. To address these challenges, we introduce Intent-driven In-context Learning for Few-shot DST (IDIC-DST). By extracting user's intent, we propose an Intent-driven Dialogue Information Augmentation module to augment the dialogue information, which can track dialogue states more effectively. Moreover, we mask noisy information from DST data and rewrite user's input in the Intent-driven Examples Retrieval module, where we retrieve similar examples. We then utilize a pre-trained large language model to update the dialogue state using the augmented dialogue information and examples. Experimental results demonstrate that IDIC-DST achieves state-of-the-art performance in few-shot settings on MultiWOZ 2.1 and MultiWOZ 2.4 datasets.