mlsanityData to 14 Oct 2026

EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text Classification

arXiv 2204.11205 ↗First posted 24 Apr 2022cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Recent works have empirically shown the effectiveness of data augmentation (DA) in NLP tasks, especially for those suffering from data scarcity. Intuitively, given the size of generated data, their diversity and quality are crucial to the performance of targeted tasks. However, to the best of our knowledge, most existing methods consider only either the diversity or the quality of augmented data, thus cannot fully mine the potential of DA for NLP. In this paper, we present an easy and plug-in data augmentation framework EPiDA to support effective text classification. EPiDA employs two mechanisms: relative entropy maximization (REM) and conditional entropy minimization (CEM) to control data generation, where REM is designed to enhance the diversity of augmented data while CEM is exploited to ensure their semantic consistency. EPiDA can support efficient and continuous data generation for effective classifier training. Extensive experiments show that EPiDA outperforms existing SOTA methods in most cases, though not using any agent networks or pre-trained generation networks, and it works well with various DA algorithms and classification models. Code is available at https://github.com/zhaominyiz/EPiDA.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 39 of its 57 references that are in the map. First posted on arXiv 24 Apr 2022.

Builds on

39 of 57 references.

References · 39

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2014Going Deeper with Convolutionscited by 4,241
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  5. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  6. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  7. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  8. 2017Decoupled Weight Decay Regularizationcited by 1,831
  9. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,127
  10. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 807
  11. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
  12. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
27 more
  1. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
  2. 2021A Survey of Data Augmentation Approaches for NLPcited by 409
  3. 2018Large Scale Crowdsourcing and Characterization of Twitter Abusive Behaviorcited by 270
  4. 2019Fast AutoAugmentcited by 243
  5. 2019SemEval-2017 Task 4: Sentiment Analysis in Twittercited by 210
  6. 2018Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relationscited by 201
  7. 2020MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classificationcited by 187
  8. 2019Not Enough Data? Deep Learning to the Rescue!cited by 175
  9. 2018QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehensioncited by 164
  10. 2014Return of the Devil in the Details: Delving Deep into Convolutional Netscited by 122
  11. 2020SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustnesscited by 96
  12. 2017Data Noising as Smoothing in Neural Network Language Modelscited by 78
  13. 2021AEDA: An Easier Data Augmentation Technique for Text Classificationcited by 67
  14. 2019Soft Contextual Data Augmentation for Neural Machine Translationcited by 49
  15. 2020Generative Data Augmentation for Commonsense Reasoningcited by 49
  16. 2020Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generationcited by 47
  17. 2019Data Augmentation via Dependency Tree Morphing for Low-Resource Languagescited by 45
  18. 2018Text Data Augmentation Made Simple By Leveraging NLP Cloud APIscited by 40
  19. 2020Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuningcited by 39
  20. 2020Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognitioncited by 36
  21. 2018Adversarial Over-Sensitivity and Over-Stability Strategies for Dialogue Modelscited by 26
  22. 2021Substructure Substitution: Structured Data Augmentation for NLPcited by 25
  23. 2021Weakly-supervised Text Classification Based on Keyword Graphcited by 25
  24. 2020Named Entity Recognition for Social Media Texts with Semantic Augmentationcited by 23
  25. 2021LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identificationcited by 16
  26. 2021Text Augmentation in a Multi-Task Viewcited by 8
  27. 2021Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Modelscited by 5

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 0; 2024: 3; 2025: 2.

7 papers.

  1. 2022PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learnerscited by 7
  2. 2024AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimescited by 1
  3. 2024Effectively Enhancing Vision Language Large Models by Prompt Augmentation and Caption Utilizationcited by 1
  4. 2025MAGE: Multi-Head Attention Guided Embeddings for Low Resource Sentiment Classificationcited by 1
  5. 2022On-the-fly Denoising for Data Augmentation in Natural Language Understandingcited by 0
  6. 2024Evaluation Metrics for Text Data Augmentation in NLPcited by 0
  7. 2025Intended Target Identification for Anomia Patients with Gradient-based Selective Augmentationcited by 0