Controllable User Dialogue Act Augmentation for Dialogue State Tracking

07/26/2022
by   Chun-Mao Lai, et al.
4

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

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/23/2020

Variational Hierarchical Dialog Autoencoder for Dialogue State Tracking Data Augmentation

Recent works have shown that generative data augmentation, where synthet...
research
08/01/2023

DiactTOD: Learning Generalizable Latent Dialogue Acts for Controllable Task-Oriented Dialogue Systems

Dialogue act annotations are important to improve response generation qu...
research
07/04/2018

Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding

In this paper, we study the problem of data augmentation for language un...
research
10/24/2020

CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers

Dialogue state trackers have made significant progress on benchmark data...
research
12/20/2016

Unsupervised Dialogue Act Induction using Gaussian Mixtures

This paper introduces a new unsupervised approach for dialogue act induc...
research
06/06/2017

A Frame Tracking Model for Memory-Enhanced Dialogue Systems

Recently, resources and tasks were proposed to go beyond state tracking ...
research
10/26/2021

Controllable Data Augmentation Through Deep Relighting

At the heart of the success of deep learning is the quality of the data....

Please sign up or login with your details

Forgot password? Click here to reset