Schema Augmentation for Zero-Shot Domain Adaptation in Dialogue State Tracking

TL;DR

This paper introduces Schema Augmentation, a fine-tuning method that enhances zero-shot domain adaptation in dialogue state tracking by varying slot names, leading to significant accuracy improvements on benchmark datasets.

Contribution

The paper proposes Schema Augmentation, a novel data augmentation technique that improves zero-shot domain adaptation for dialogue state tracking through schema variation during fine-tuning.

Findings

Over twofold accuracy gain on unseen domains.

Maintains or improves performance across all domains.

Effective alternative to prompt engineering in zero-shot adaptation.

Abstract

Zero-shot domain adaptation for dialogue state tracking (DST) remains a challenging problem in task-oriented dialogue (TOD) systems, where models must generalize to target domains unseen at training time. Current large language model approaches for zero-shot domain adaptation rely on prompting to introduce knowledge pertaining to the target domains. However, their efficacy strongly depends on prompt engineering, as well as the zero-shot ability of the underlying language model. In this work, we devise a novel data augmentation approach, Schema Augmentation, that improves the zero-shot domain adaptation of language models through fine-tuning. Schema Augmentation is a simple but effective technique that enhances generalization by introducing variations of slot names within the schema provided in the prompt. Experiments on MultiWOZ and SpokenWOZ showed that the proposed approach resulted in a substantial improvement over the baseline, in some experiments achieving over a twofold accuracy gain over unseen domains while maintaining equal or superior performance over all domains.