Controllable User Dialogue Act Augmentation for Dialogue State Tracking

TL;DR

This paper introduces CUDA-DST, a controllable data augmentation method for dialogue state tracking that enhances diversity and robustness of user utterances, leading to improved performance on the MultiWOZ 2.1 dataset.

Contribution

It proposes a novel controllable augmentation technique that covers diverse dialogue acts, improving generalization and robustness of dialogue state trackers.

Findings

Achieves state-of-the-art performance on MultiWOZ 2.1

Improves robustness of dialogue state tracking models

Enhances diversity of user utterance data

Abstract

Prior work has demonstrated that data augmentation is useful for improving dialogue state tracking. However, there are many types of user utterances, while the prior method only considered the simplest one for augmentation, raising the concern about poor generalization capability. In order to better cover diverse dialogue acts and control the generation quality, this paper proposes controllable user dialogue act augmentation (CUDA-DST) to augment user utterances with diverse behaviors. With the augmented data, different state trackers gain improvement and show better robustness, achieving the state-of-the-art performance on MultiWOZ 2.1