mlsanityData to 7 Oct 2026

Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study

arXiv 1808.05697 ↗First posted 16 Aug 2018cs.CL cs.LG stat.MLcited by 90

Not on the map. Why?

Abstract (arXiv)

Several recent papers investigate Active Learning (AL) for mitigating the data dependence of deep learning for natural language processing. However, the applicability of AL to real-world problems remains an open question. While in supervised learning, practitioners can try many different methods, evaluating each against a validation set before selecting a model, AL affords no such luxury. Over the course of one AL run, an agent annotates its dataset exhausting its labeling budget. Thus, given a new task, an active learner has no opportunity to compare models and acquisition functions. This paper provides a large scale empirical study of deep active learning, addressing multiple tasks and, for each, multiple datasets, multiple models, and a full suite of acquisition functions. We find that across all settings, Bayesian active learning by disagreement, using uncertainty estimates provided either by Dropout or Bayes-by Backprop significantly improves over i.i.d. baselines and usually outperforms classic uncertainty sampling.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 27; 2022: 16; 2023: 23; 2024: 11; 2025: 8; 2026: 5.

90 papers.

Sort:

By area:

  1. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 337
  2. 2021Active Learning by Acquiring Contrastive Examplescited by 154
  3. 2023Modern Bayesian Experimental Designcited by 121
  4. 2022Plex: Towards Reliability using Pretrained Large Model Extensionscited by 102
  5. 2021On Statistical Bias In Active Learning: How and When To Fix Itcited by 72
  6. 2021Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answeringcited by 62
  7. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  8. 2023Prediction-Oriented Bayesian Active Learningcited by 60
  9. 2023Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Taskscited by 53
  10. 2022AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languagescited by 46
  11. 2023Uncertainty in Natural Language Processing: Sources, Quantification, and Applicationscited by 44
  12. 2022A Survey of Active Learning for Natural Language Processingcited by 40
38 more
  1. 2021Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimatescited by 39
  2. 2021On the Importance of Effectively Adapting Pretrained Language Models for Active Learningcited by 31
  3. 2024Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Modelscited by 29
  4. 2021Cartography Active Learningcited by 26
  5. 2023The Efficiency Spectrum of Large Language Models: An Algorithmic Surveycited by 25
  6. 2022Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcitycited by 24
  7. 2021Uncertainty-Aware Reliable Text Classificationcited by 23
  8. 2021Diversity Enhanced Active Learning with Strictly Proper Scoring Rulescited by 22
  9. 2022BayesFormer: Transformer with Uncertainty Estimationcited by 19
  10. 2024Deep Bayesian Active Learning for Preference Modeling in Large Language Modelscited by 19
  11. 2021Deep Learning for Bayesian Optimization of Scientific Problems with High-Dimensional Structurecited by 15
  12. 2023CAVEN: An Embodied Conversational Agent for Efficient Audio-Visual Navigation in Noisy Environmentscited by 14
  13. 2022Make The Most of Prior Data: A Solution for Interactive Text Summarization with Preference Feedbackcited by 13
  14. 2024A Framework for Efficient Model Evaluation through Stratification, Sampling, and Estimationcited by 13
  15. 2021Multi-class Text Classification using BERT-based Active Learningcited by 11
  16. 2021Should We Trust This Summary? Bayesian Abstractive Summarization to The Rescuecited by 11
  17. 2022Active Learning Over Multiple Domains in Natural Language Taskscited by 11
  18. 2022Towards Computationally Feasible Deep Active Learningcited by 11
  19. 2023Disentangled Multi-Fidelity Deep Bayesian Active Learningcited by 11
  20. 2025Explainability in Practice: A Survey of Explainable NLP Across Various Domainscited by 11
  21. 2023Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networkscited by 10
  22. 2021Diversity-Aware Batch Active Learning for Dependency Parsingcited by 9
  23. 2021Bayesian Active Learning by Disagreements: A Geometric Perspectivecited by 9
  24. 2023On the Limitations of Simulating Active Learningcited by 9
  25. 2023GAD-PVI: A General Accelerated Dynamic-Weight Particle-Based Variational Inference Frameworkcited by 9
  26. 2021Annotation Curricula to Implicitly Train Non-Expert Annotatorscited by 8
  27. 2021LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service Frameworkcited by 8
  28. 2021Deep Bayesian Active Learning for Accelerating Stochastic Simulationcited by 7
  29. 2024Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentationcited by 7
  30. 2021Active2 Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translationcited by 6
  31. 2023Active Learning for Abstractive Text Summarizationcited by 6
  32. 2023Investigating Multi-source Active Learning for Natural Language Inferencecited by 6
  33. 2023Bayesian Estimate of Mean Proper Scores for Diversity-Enhanced Active Learningcited by 6
  34. 2024Language Model-Driven Data Pruning Enables Efficient Active Learningcited by 6
  35. 2021Deep Active Learning for Text Classification with Diverse Interpretationscited by 5
  36. 2021Bayesian Active Summarizationcited by 5
  37. 2022TrustAL: Trustworthy Active Learning using Knowledge Distillationcited by 5
  38. 2022Combining Data Generation and Active Learning for Low-Resource Question Answeringcited by 5

50 most cited of 90 All 90 (JSON)