mlsanityData to 7 Oct 2026

Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning

arXiv 2103.07552 ↗First posted 12 Mar 2021cs.CLcited by 35

Not on the map. Why?

Abstract (arXiv)

Few-shot text classification is a fundamental NLP task in which a model aims to classify text into a large number of categories, given only a few training examples per category. This paper explores data augmentation -- a technique particularly suitable for training with limited data -- for this few-shot, highly-multiclass text classification setting. On four diverse text classification tasks, we find that common data augmentation techniques can improve the performance of triplet networks by up to 3.0% on average. To further boost performance, we present a simple training strategy called curriculum data augmentation, which leverages curriculum learning by first training on only original examples and then introducing augmented data as training progresses. We explore a two-stage and a gradual schedule, and find that, compared with standard single-stage training, curriculum data augmentation trains faster, improves performance, and remains robust to high amounts of noising from augmentation.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 18 of its 29 references that are in the map. First posted on arXiv 12 Mar 2021.

Builds on

18 of 29 references.

References · 18

  1. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  2. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  3. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  4. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
  5. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  6. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  7. 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
  8. 2018Cooperative Learning of Audio and Video Models from Self-Supervised Synchronizationcited by 246
  9. 2019Good-Enough Compositional Data Augmentationcited by 158
  10. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 153
  11. 2018Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networkscited by 113
  12. 2016Edinburgh Neural Machine Translation Systems for WMT 16cited by 76
6 more
  1. 2018SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translationcited by 72
  2. 2016Attentive Pooling Networkscited by 28
  3. 2016Learning the Curriculum with Bayesian Optimization for Task-Specific Word Representation Learningcited by 22
  4. 2020What Are People Asking About COVID-19? A Question Classification Datasetcited by 5
  5. 2020Rethinking Curriculum Learning with Incremental Labels and Adaptive Compensationcited by 4
  6. 2020Context-based Transformer Models for Answer Sentence Selectioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 9; 2023: 10; 2024: 10; 2025: 2; 2026: 1.

35 papers.

Sort:

By area:

  1. 2021A Survey of Data Augmentation Approaches for NLPcited by 408
  2. 2023AugGPT: Leveraging ChatGPT for Text Data Augmentationcited by 128
  3. 2022Data-Efficient Finetuning Using Cross-Task Nearest Neighborscited by 26
  4. 2024RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Contentcited by 26
  5. 2023Mask-guided BERT for Few Shot Text Classificationcited by 25
  6. 2023PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillationcited by 25
  7. 2023Exploring New Frontiers in Agricultural NLP: Investigating the Potential of Large Language Models for Food Applicationscited by 21
  8. 2022Imagination-Augmented Natural Language Understandingcited by 19
  9. 2022Contrastive Learning for Prompt-Based Few-Shot Language Learnerscited by 17
  10. 2021Efficient Contrastive Learning via Novel Data Augmentation and Curriculum Learningcited by 14
  11. 2022PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentationcited by 14
  12. 2023Curricular Object Manipulation in LiDAR-based Object Detectioncited by 12
23 more
  1. 2024Evolving Knowledge Distillation with Large Language Models and Active Learningcited by 12
  2. 2023Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLMcited by 11
  3. 2024Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Bettercited by 11
  4. 2024NICE: To Optimize In-Context Examples or Not?cited by 9
  5. 2023Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Modelscited by 6
  6. 2021Good-Enough Example Extrapolationcited by 5
  7. 2022Embedding Hallucination for Few-Shot Language Fine-tuningcited by 5
  8. 2022SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Trainingcited by 5
  9. 2022AugCSE: Contrastive Sentence Embedding with Diverse Augmentationscited by 5
  10. 2024One size doesn't fit all: Predicting the Number of Examples for In-Context Learningcited by 4
  11. 2022DialAug: Mixing up Dialogue Contexts in Contrastive Learning for Robust Conversational Modelingcited by 3
  12. 2023BLIAM: Literature-based Data Synthesis for Synergistic Drug Combination Predictioncited by 3
  13. 2024Improving Zero-Shot Cross-Lingual Transfer via Progressive Code-Switchingcited by 3
  14. 2024Enhancing Graph Neural Networks with Limited Labeled Data by Actively Distilling Knowledge from Large Language Modelscited by 3
  15. 2022A Curriculum Learning Approach for Multi-domain Text Classification Using Keyword weight Rankingcited by 2
  16. 2023Data Augmentation for Neural NLPcited by 2
  17. 2024Colorful Cutout: Enhancing Image Data Augmentation with Curriculum Learningcited by 2
  18. 2023EXnet: Efficient In-context Learning for Data-less Text classificationcited by 1
  19. 2024Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentationcited by 1
  20. 2024Adverb Is the Key: Simple Text Data Augmentation with Adverb Deletioncited by 0
  21. 2025Implicit Word Reordering with Knowledge Distillation for Cross-Lingual Dependency Parsingcited by 0
  22. 2025A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domainscited by 0
  23. 2026Disentangling Curriculum Learning in NLP: Towards a Unifying Taxonomycited by 0