mlsanityData to 7 Oct 2026

Augmenting Data with Mixup for Sentence Classification: An Empirical Study

arXiv 1905.08941 ↗First posted 22 May 2019cs.CL cs.AIcited by 125

Not on the map. Why?

Abstract (arXiv)

Mixup, a recent proposed data augmentation method through linearly interpolating inputs and modeling targets of random samples, has demonstrated its capability of significantly improving the predictive accuracy of the state-of-the-art networks for image classification. However, how this technique can be applied to and what is its effectiveness on natural language processing (NLP) tasks have not been investigated. In this paper, we propose two strategies for the adaption of Mixup on sentence classification: one performs interpolation on word embeddings and another on sentence embeddings. We conduct experiments to evaluate our methods using several benchmark datasets. Our studies show that such interpolation strategies serve as an effective, domain independent data augmentation approach for sentence classification, and can result in significant accuracy improvement for both CNN and LSTM models.

Key facts. Cited by 125 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 32; 2022: 36; 2023: 22; 2024: 23; 2025: 6; 2026: 6.

125 papers.

Sort:

By area:

  1. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 337
  2. 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 145
  3. 2021A Survey on Data Augmentation for Text Classificationcited by 111
  4. 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
  5. 2021Data Augmentation Approaches in Natural Language Processing: A Surveycited by 82
  6. 2022MixGen: A New Multi-Modal Data Augmentationcited by 61
  7. 2022Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Modulecited by 43
  8. 2021SSMix: Saliency-Based Span Mixup for Text Classificationcited by 39
  9. 2021MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognitioncited by 38
  10. 2024A Comprehensive Survey on Data Augmentationcited by 38
  11. 2022On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliencycited by 31
  12. 2022MixAugment & Mixup: Augmentation Methods for Facial Expression Recognitioncited by 31
38 more
  1. 2021Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservationcited by 30
  2. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
  3. 2025MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusioncited by 30
  4. 2021RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Modelscited by 28
  5. 2022A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspectivecited by 27
  6. 2021Substructure Substitution: Structured Data Augmentation for NLPcited by 25
  7. 2021Survey: Image Mixing and Deleting for Data Augmentationcited by 25
  8. 2021Contrastive Vision-Language Pre-training with Limited Resourcescited by 25
  9. 2022A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generationcited by 25
  10. 2022Interpolation-based Contrastive Learning for Few-Label Semi-Supervised Learningcited by 23
  11. 2021Reweighting Augmented Samples by Minimizing the Maximal Expected Losscited by 21
  12. 2022Mixed Graph Contrastive Network for Semi-Supervised Node Classificationcited by 21
  13. 2023Using GPT-4 to Augment Unbalanced Data for Automatic Scoringcited by 20
  14. 2023The Benefits of Mixup for Feature Learningcited by 19
  15. 2024A Survey on Mixup Augmentations and Beyondcited by 18
  16. 2021AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentationcited by 17
  17. 2024Empowering Large Language Models for Textual Data Augmentationcited by 17
  18. 2021LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identificationcited by 16
  19. 2022TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understandingcited by 15
  20. 2022GraphMAD: Graph Mixup for Data Augmentation using Data-Driven Convex Clusteringcited by 13
  21. 2023Over-training with Mixup May Hurt Generalizationcited by 13
  22. 2021Connecting Language and Vision for Natural Language-Based Vehicle Retrievalcited by 12
  23. 2021To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLPcited by 12
  24. 2021MixUp Training Leads to Reduced Overfitting and Improved Calibration for the Transformer Architecturecited by 11
  25. 2022GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentationcited by 11
  26. 2021Data Augmentation in a Hybrid Approach for Aspect-Based Sentiment Analysiscited by 10
  27. 2021Consistency Training with Virtual Adversarial Discrete Perturbationcited by 9
  28. 2021Transforming Fake News: Robust Generalisable News Classification Using Transformerscited by 8
  29. 2022Exploring Representation-Level Augmentation for Code Searchcited by 8
  30. 2024LLM-based Privacy Data Augmentation Guided by Knowledge Distillation with a Distribution Tutor for Medical Text Classificationcited by 8
  31. 2024ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptionscited by 8
  32. 2024CMamba: Channel Correlation Enhanced State Space Models for Multivariate Time Series Forecastingcited by 8
  33. 2024A Survey of Data Synthesis Approachescited by 8
  34. 2021Influence-guided Data Augmentation for Neural Tensor Completioncited by 7
  35. 2021Distiller: A Systematic Study of Model Distillation Methods in Natural Language Processingcited by 7
  36. 2021ifMixup: Interpolating Graph Pair to Regularize Graph Classificationcited by 7
  37. 2022Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translationcited by 7
  38. 2022PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learnerscited by 7

50 most cited of 125 All 125 (JSON)