mlsanityData to 14 Oct 2026

Uncertainty Sentence Sampling by Virtual Adversarial Perturbation

arXiv 2210.14576 ↗First posted 26 Oct 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Active learning for sentence understanding attempts to reduce the annotation cost by identifying the most informative examples. Common methods for active learning use either uncertainty or diversity sampling in the pool-based scenario. In this work, to incorporate both predictive uncertainty and sample diversity, we propose Virtual Adversarial Perturbation for Active Learning (VAPAL) , an uncertainty-diversity combination framework, using virtual adversarial perturbation (Miyato et al., 2019) as model uncertainty representation. VAPAL consistently performs equally well or even better than the strong baselines on four sentence understanding datasets: AGNEWS, IMDB, PUBMED, and SST-2, offering a potential option for active learning on sentence understanding tasks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 32 references that are in the map. First posted on arXiv 26 Oct 2022.

Builds on

17 of 32 references.

References · 17

  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. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  5. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  6. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  7. 2016Adversarial examples in the physical worldcited by 1,769
  8. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,414
  9. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  10. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  11. 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
  12. 2020Cold-start Active Learning through Self-supervised Language Modelingcited by 128
5 more
  1. 2017PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstractscited by 124
  2. 2019Discriminative Active Learningcited by 98
  3. 2017Deep Active Learning over the Long Tailcited by 84
  4. 2015Distributional Smoothing with Virtual Adversarial Trainingcited by 61
  5. 2021Industry Scale Semi-Supervised Learning for Natural Language Understandingcited by 3

Built on by

Not cited yet.