Improving Limited Labeled Dialogue State Tracking with Self-Supervision
- URL: http://arxiv.org/abs/2010.13920v1
- Date: Mon, 26 Oct 2020 21:57:42 GMT
- Title: Improving Limited Labeled Dialogue State Tracking with Self-Supervision
- Authors: Chien-Sheng Wu and Steven Hoi and Caiming Xiong
- Abstract summary: Existing dialogue state tracking (DST) models require plenty of labeled data.
We present and investigate two self-supervised objectives: preserving latent consistency and modeling conversational behavior.
Our proposed self-supervised signals can improve joint goal accuracy by 8.95% when only 1% labeled data is used.
- Score: 91.68515201803986
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
Err
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.