mlsanityData to 7 Oct 2026

Are Data Augmentation Methods in Named Entity Recognition Applicable for Uncertainty Estimation?

arXiv 2407.02062 ↗First posted 2 Jul 2024cs.CL cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

This work investigates the impact of data augmentation on confidence calibration and uncertainty estimation in Named Entity Recognition (NER) tasks. For the future advance of NER in safety-critical fields like healthcare and finance, it is essential to achieve accurate predictions with calibrated confidence when applying Deep Neural Networks (DNNs), including Pre-trained Language Models (PLMs), as a real-world application. However, DNNs are prone to miscalibration, which limits their applicability. Moreover, existing methods for calibration and uncertainty estimation are computational expensive. Our investigation in NER found that data augmentation improves calibration and uncertainty in cross-genre and cross-lingual setting, especially in-domain setting. Furthermore, we showed that the calibration for NER tends to be more effective when the perplexity of the sentences generated by data augmentation is lower, and that increasing the size of the augmentation further improves calibration and uncertainty.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 33 of its 62 references that are in the map. First posted on arXiv 2 Jul 2024.

Builds on

33 of 62 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  7. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  8. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  9. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  10. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  11. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  12. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
21 more
  1. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  2. 2016Neural Architectures for Named Entity Recognitioncited by 548
  3. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 461
  4. 2020Calibration of Pre-trained Transformerscited by 307
  5. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 208
  6. 2023Large Language Models for Generative Information Extraction: A Surveycited by 183
  7. 2021A Unified Generative Framework for Various NER Subtaskscited by 141
  8. 2018Quantifying Uncertainties in Natural Language Processing Taskscited by 79
  9. 2020An Analysis of Simple Data Augmentation for Named Entity Recognitioncited by 75
  10. 2023Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languagescited by 61
  11. 2021When and How Mixup Improves Calibrationcited by 59
  12. 2021SpanNER: Named Entity Re-/Recognition as Span Predictioncited by 55
  13. 2020Combining Ensembles and Data Augmentation can Harm your Calibrationcited by 44
  14. 2021MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NERcited by 42
  15. 2023What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifierscited by 35
  16. 2020Local Additivity Based Data Augmentation for Semi-supervised NERcited by 31
  17. 2024Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challengescited by 30
  18. 2022Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcitycited by 24
  19. 2021Data Augmentation for Cross-Domain Named Entity Recognitioncited by 14
  20. 2020Ensemble Distillation for Structured Prediction: Calibrated, Accurate, Fast-Choose Threecited by 8
  21. 2023Bag of Tricks for In-Distribution Calibration of Pretrained Transformerscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Modelscited by 3
  2. 2025The Effects of Data Augmentation on Confidence Estimation for LLMscited by 0
  3. 2026On-Device Named-Entity Recognition: A Deployability Study of Accuracy, Cost, Reliability, and Confidencecited by 0