mlsanityData to 7 Oct 2026

Re-weighting Tokens: A Simple and Effective Active Learning Strategy for Named Entity Recognition

arXiv 2311.00906 ↗First posted 2 Nov 2023cs.CL cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Active learning, a widely adopted technique for enhancing machine learning models in text and image classification tasks with limited annotation resources, has received relatively little attention in the domain of Named Entity Recognition (NER). The challenge of data imbalance in NER has hindered the effectiveness of active learning, as sequence labellers lack sufficient learning signals. To address these challenges, this paper presents a novel reweighting-based active learning strategy that assigns dynamic smoothed weights to individual tokens. This adaptable strategy is compatible with various token-level acquisition functions and contributes to the development of robust active learners. Experimental results on multiple corpora demonstrate the substantial performance improvement achieved by incorporating our re-weighting strategy into existing acquisition functions, validating its practical efficacy.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 22 of its 42 references that are in the map. First posted on arXiv 2 Nov 2023.

Builds on

22 of 42 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  4. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  5. 2017Deep Bayesian Active Learning with Image Datacited by 812
  6. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  7. 2016Neural Architectures for Named Entity Recognitioncited by 548
  8. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  9. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  10. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 174
  11. 2015Cost Sensitive Learning of Deep Feature Representations from Imbalanced Datacited by 167
  12. 2020Feature Space Augmentation for Long-Tailed Datacited by 136
10 more
  1. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
  2. 2020Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspectivecited by 120
  3. 2018Gradient Harmonized Single-stage Detectorcited by 114
  4. 2017Deep Active Learning for Named Entity Recognitioncited by 108
  5. 2020Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learningcited by 105
  6. 2020SeqMix: Augmenting Active Sequence Labeling via Sequence Mixupcited by 52
  7. 2021Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimatescited by 39
  8. 2021Deep Active Learning by Leveraging Training Dynamicscited by 32
  9. 2022Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernelscited by 25
  10. 2021Diversity Enhanced Active Learning with Strictly Proper Scoring Rulescited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2024What is Wrong with Perplexity for Long-context Language Modeling?cited by 68
  2. 2024How Can I Improve? Using GPT to Highlight the Desired and Undesired Parts of Open-ended Responsescited by 10
  3. 2026Rethinking Personalization in Large Language Models at the Token Levelcited by 3
  4. 2025SFT-GO: Supervised Fine-Tuning with Group Optimization for Large Language Modelscited by 2