mlsanityData to 14 Oct 2026

MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification

arXiv 2004.12239 ↗First posted 25 Apr 2020cs.CL cs.LGcited by 187

Not on the map. Why?

Abstract (arXiv)

This paper presents MixText, a semi-supervised learning method for text classification, which uses our newly designed data augmentation method called TMix. TMix creates a large amount of augmented training samples by interpolating text in hidden space. Moreover, we leverage recent advances in data augmentation to guess low-entropy labels for unlabeled data, hence making them as easy to use as labeled data.By mixing labeled, unlabeled and augmented data, MixText significantly outperformed current pre-trained and fined-tuned models and other state-of-the-art semi-supervised learning methods on several text classification benchmarks. The improvement is especially prominent when supervision is extremely limited. We have publicly released our code at https://github.com/GT-SALT/MixText.

Key facts. Cited by 187 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 42; 2022: 50; 2023: 52; 2024: 23; 2025: 11; 2026: 9.

187 papers.

Sort:

By area:

  1. 2021True Few-Shot Learning with Language Modelscited by 344
  2. 2021A Survey on Deep Semi-supervised Learningcited by 251
  3. 2023Data-centric Artificial Intelligence: A Surveycited by 203
  4. 2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
  5. 2021GPT3Mix: Leveraging Large-scale Language Models for Text Augmentationcited by 187
  6. 2021Noisy Channel Language Model Prompting for Few-Shot Text Classificationcited by 165
  7. 2023Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventionscited by 125
  8. 2021A Survey on Data Augmentation for Text Classificationcited by 111
  9. 2021Measure and Improve Robustness in NLP Models: A Surveycited by 107
  10. 2023Text Classification via Large Language Modelscited by 106
  11. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  12. 2023Waffling around for Performance: Visual Classification with Random Words and Broad Conceptscited by 101
38 more
  1. 2021Improving and Simplifying Pattern Exploiting Trainingcited by 97
  2. 2022USB: A Unified Semi-supervised Learning Benchmark for Classificationcited by 95
  3. 2021Continual Learning for Text Classification with Information Disentanglement Based Regularizationcited by 86
  4. 2022STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translationcited by 57
  5. 2024Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluationcited by 57
  6. 2022Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Modulecited by 44
  7. 2021A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned and Perspectivescited by 41
  8. 2021Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Trainingcited by 41
  9. 2021SSMix: Saliency-Based Span Mixup for Text Classificationcited by 39
  10. 2021True Few-Shot Learning with Prompts -- A Real-World Perspectivecited by 38
  11. 2022Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learningcited by 36
  12. 2021HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalizationcited by 32
  13. 2021FlipDA: Effective and Robust Data Augmentation for Few-Shot Learningcited by 32
  14. 2022On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliencycited by 31
  15. 2022Continual Sequence Generation with Adaptive Compositional Modulescited by 31
  16. 2022MixAugment & Mixup: Augmentation Methods for Facial Expression Recognitioncited by 31
  17. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 31
  18. 2024A Survey on Data Augmentation in Large Model Eracited by 31
  19. 2022Enhancing Cross-lingual Transfer by Manifold Mixupcited by 30
  20. 2025Shifting AI Efficiency From Model-Centric to Data-Centric Compressioncited by 29
  21. 2021Self-supervised Dialogue Learning for Spoken Conversational Question Answeringcited by 28
  22. 2021Learning with Different Amounts of Annotation: From Zero to Many Labelscited by 28
  23. 2021The Rich Get Richer: Disparate Impact of Semi-Supervised Learningcited by 28
  24. 2024Scalable Language Model with Generalized Continual Learningcited by 28
  25. 2021Pre-train or Annotate? Domain Adaptation with a Constrained Budgetcited by 27
  26. 2024Heterogeneous Contrastive Learning for Foundation Models and Beyondcited by 27
  27. 2021Survey: Image Mixing and Deleting for Data Augmentationcited by 26
  28. 2022Robustness Analysis of Video-Language Models Against Visual and Language Perturbationscited by 23
  29. 2023Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learnercited by 23
  30. 2023FedET: A Communication-Efficient Federated Class-Incremental Learning Framework Based on Enhanced Transformercited by 23
  31. 2023Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Modelscited by 20
  32. 2024A Survey on Mixup Augmentations and Beyondcited by 20
  33. 2021Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systemscited by 18
  34. 2021AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentationcited by 17
  35. 2023Rethinking Semi-supervised Learning with Language Modelscited by 17
  36. 2021Weakly-Supervised Hierarchical Models for Predicting Persuasive Strategies in Good-faith Textual Requestscited by 16
  37. 2021Cross-SEAN: A Cross-Stitch Semi-Supervised Neural Attention Model for COVID-19 Fake News Detectioncited by 15
  38. 2022TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understandingcited by 15

50 most cited of 187 All 187 (JSON)