Improving Limited Labeled Dialogue State Tracking with Self-Supervision

by   Chien-Sheng Wu, et al.

Existing dialogue state tracking (DST) models require plenty of labeled data. However, collecting high-quality labels is costly, especially when the number of domains increases. In this paper, we address a practical DST problem that is rarely discussed, i.e., learning efficiently with limited labeled data. We present and investigate two self-supervised objectives: preserving latent consistency and modeling conversational behavior. We encourage a DST model to have consistent latent distributions given a perturbed input, making it more robust to an unseen scenario. We also add an auxiliary utterance generation task, modeling a potential correlation between conversational behavior and dialogue states. The experimental results show that our proposed self-supervised signals can improve joint goal accuracy by 8.95% when only 1% labeled data is used on the MultiWOZ dataset. We can achieve an additional 1.76% improvement if some unlabeled data is jointly trained as semi-supervised learning. We analyze and visualize how our proposed self-supervised signals help the DST task and hope to stimulate future data-efficient DST research.


page 1

page 2

page 3

page 4


CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking

Few-shot dialogue state tracking (DST) is a realistic problem that train...

Self-semi-supervised Learning to Learn from NoisyLabeled Data

The remarkable success of today's deep neural networks highly depends on...

Large-Context Conversational Representation Learning: Self-Supervised Learning for Conversational Documents

This paper presents a novel self-supervised learning method for handling...

Conversational Query Rewriting with Self-supervised Learning

Context modeling plays a critical role in building multi-turn dialogue s...

DialogZoo: Large-Scale Dialog-Oriented Task Learning

Building unified conversational agents has been a long-standing goal of ...

Semi-Supervised Few-Shot Learning for Dual Question-Answer Extraction

This paper addresses the problem of key phrase extraction from sentences...

Social Processes: Self-Supervised Forecasting of Nonverbal Cues in Social Conversations

The default paradigm for the forecasting of human behavior in social con...

Please sign up or login with your details

Forgot password? Click here to reset