Intent-driven In-context Learning for Few-shot Dialogue State Tracking

TL;DR

This paper introduces IDIC-DST, a novel intent-driven in-context learning approach that enhances few-shot dialogue state tracking by augmenting dialogue information and retrieving similar examples, achieving state-of-the-art results.

Contribution

The paper proposes a new intent-driven in-context learning method for few-shot DST that effectively handles implicit information and noise in dialogue data.

Findings

Achieves state-of-the-art performance on MultiWOZ datasets.

Effectively handles implicit and noisy dialogue information.

Improves dialogue state tracking accuracy in few-shot scenarios.

Abstract

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.