mlsanityData to 7 Oct 2026

SSMix: Saliency-Based Span Mixup for Text Classification

arXiv 2106.08062 ↗First posted 15 Jun 2021cs.CL cs.AI cs.LGcited by 39

Not on the map. Why?

Abstract (arXiv)

Data augmentation with mixup has shown to be effective on various computer vision tasks. Despite its great success, there has been a hurdle to apply mixup to NLP tasks since text consists of discrete tokens with variable length. In this work, we propose SSMix, a novel mixup method where the operation is performed on input text rather than on hidden vectors like previous approaches. SSMix synthesizes a sentence while preserving the locality of two original texts by span-based mixing and keeping more tokens related to the prediction relying on saliency information. With extensive experiments, we empirically validate that our method outperforms hidden-level mixup methods on a wide range of text classification benchmarks, including textual entailment, sentiment classification, and question-type classification. Our code is available at https://github.com/clovaai/ssmix.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 21 of its 31 references that are in the map. First posted on arXiv 15 Jun 2021.

Builds on

21 of 31 references.

References · 21

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  2. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  3. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  4. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  5. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  7. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
  8. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 798
  9. 2021A Survey of Data Augmentation Approaches for NLPcited by 408
  10. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  11. 2019FreeLB: Enhanced Adversarial Training for Natural Language Understandingcited by 261
  12. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 260
9 more
  1. 2015Visualizing and Understanding Neural Models in NLPcited by 199
  2. 2020MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classificationcited by 186
  3. 2020SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularizationcited by 149
  4. 2019Augmenting Data with Mixup for Sentence Classification: An Empirical Studycited by 125
  5. 2020SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustnesscited by 94
  6. 2018NSML: Meet the MLaaS platform with a real-world case studycited by 70
  7. 2017NSML: A Machine Learning Platform That Enables You to Focus on Your Modelscited by 34
  8. 2019Data Augmentation Revisited: Rethinking the Distribution Gap between Clean and Augmented Datacited by 33
  9. 2021Consistency Training with Virtual Adversarial Discrete Perturbationcited by 9

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 16; 2023: 10; 2024: 6; 2025: 6.

39 papers.

Sort:

By area:

  1. 2022Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Modulecited by 43
  2. 2024A Comprehensive Survey on Data Augmentationcited by 38
  3. 2022On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliencycited by 31
  4. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
  5. 2022Geodesic Multi-Modal Mixup for Robust Fine-Tuningcited by 29
  6. 2022On the Domain Adaptation and Generalization of Pretrained Language Models: A Surveycited by 22
  7. 2023Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learningcited by 18
  8. 2024A Survey on Mixup Augmentations and Beyondcited by 18
  9. 2022TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understandingcited by 15
  10. 2022Improving the Sample Efficiency of Prompt Tuning with Domain Adaptationcited by 15
  11. 2022DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classificationcited by 10
  12. 2022SelfMix: Robust Learning Against Textual Label Noise with Self-Mixup Trainingcited by 8
27 more
  1. 2023Interdisciplinary Fairness in Imbalanced Research Proposal Topic Inference: A Hierarchical Transformer-based Method with Selective Interpolationcited by 8
  2. 2021LINDA: Unsupervised Learning to Interpolate in Natural Language Processingcited by 6
  3. 2022MixKG: Mixing for harder negative samples in knowledge graphcited by 5
  4. 2023Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Taskscited by 5
  5. 2023SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentationcited by 5
  6. 2022MIXCODE: Enhancing Code Classification by Mixup-Based Data Augmentationcited by 4
  7. 2022Beyond Instance Discrimination: Relation-aware Contrastive Self-supervised Learningcited by 4
  8. 2023Data Augmentation for Conversational AIcited by 3
  9. 2025SMOTExT: SMOTE meets Large Language Modelscited by 3
  10. 2025LM-mixup: Text Data Augmentation via Language Model based Mixupcited by 3
  11. 2022On the Effectiveness of Hybrid Pooling in Mixup-Based Graph Learning for Language Processingcited by 2
  12. 2022SMSMix: Sense-Maintained Sentence Mixup for Word Sense Disambiguationcited by 2
  13. 2023AttentionMix: Data augmentation method that relies on BERT attention mechanismcited by 2
  14. 2024ICON: Improving Inter-Report Consistency in Radiology Report Generation via Lesion-aware Mixup Augmentationcited by 2
  15. 2025Scan-and-Print: Patch-level Data Summarization and Augmentation for Content-aware Layout Generation in Poster Designcited by 2
  16. 2025Mitigating Shortcut Learning with InterpoLated Learningcited by 2
  17. 2022Hierarchical MixUp Multi-label Classification with Imbalanced Interdisciplinary Research Proposalscited by 1
  18. 2023AMPLIFY:Attention-based Mixup for Performance Improvement and Label Smoothing in Transformercited by 1
  19. 2023PowMix: A Versatile Regularizer for Multimodal Sentiment Analysiscited by 1
  20. 2024AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimescited by 1
  21. 2024Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentationcited by 1
  22. 2025Language-Informed Hyperspectral Image Synthesis for Imbalanced-Small Sample Classification via Semi-Supervised Conditional Diffusion Modelcited by 1
  23. 2022Feature Weaken: Vicinal Data Augmentation for Classificationcited by 0
  24. 2023MSMix:An Interpolation-Based Text Data Augmentation Method Manifold Swap Mixupcited by 0
  25. 2023Mixup-Augmented Meta-Learning for Sample-Efficient Fine-Tuning of Protein Simulatorscited by 0
  26. 2024ALVIN: Active Learning Via INterpolationcited by 0
  27. 2025Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projectionscited by 0