mlsanityData to 14 Oct 2026

Self-Training with Purpose Preserving Augmentation Improves Few-shot Generative Dialogue State Tracking

arXiv 2211.09379 ↗First posted 17 Nov 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

In dialogue state tracking (DST), labeling the dataset involves considerable human labor. We propose a new self-training framework for few-shot generative DST that utilize unlabeled data. Our self-training method iteratively improves the model by pseudo labeling and employs Purpose Preserving Augmentation (PPAug) to prevent overfitting. We increaese the few-shot 10% performance by approximately 4% on MultiWOZ 2.1 and enhances the slot-recall 8.34% for unseen values compared to baseline.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 25 references that are in the map. First posted on arXiv 17 Nov 2022.

Builds on

19 of 25 references.

References · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  5. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  6. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 807
  7. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
  8. 2019Confidence Regularized Self-Trainingcited by 419
  9. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 216
  10. 2019Revisiting Self-Training for Neural Sequence Generationcited by 155
  11. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  12. 2020Self-training Improves Pre-training for Natural Language Understandingcited by 96
7 more
  1. 2021AEDA: An Easier Data Augmentation Technique for Text Classificationcited by 67
  2. 2021Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Trackingcited by 61
  3. 2020CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackerscited by 43
  4. 2020From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gapcited by 40
  5. 2021STraTA: Self-Training with Task Augmentation for Better Few-shot Learningcited by 33
  6. 2021Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systemscited by 18
  7. 2021Few Shot Dialogue State Tracking using Meta-learningcited by 16

Built on by

Not cited yet.