mlsanityData to 14 Oct 2026

Good-Enough Example Extrapolation

arXiv 2109.05602 ↗First posted 12 Sep 2021cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

This paper asks whether extrapolating the hidden space distribution of text examples from one class onto another is a valid inductive bias for data augmentation. To operationalize this question, I propose a simple data augmentation protocol called "good-enough example extrapolation" (GE3). GE3 is lightweight and has no hyperparameters. Applied to three text classification datasets for various data imbalance scenarios, GE3 improves performance more than upsampling and other hidden-space data augmentation methods.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 12 Sep 2021.

Builds on

25 of 36 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  5. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  6. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  7. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 807
  8. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
  9. 2021A Survey of Data Augmentation Approaches for NLPcited by 409
  10. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 377
  11. 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
  12. 2018Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relationscited by 201
13 more
  1. 2020MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classificationcited by 187
  2. 2019Good-Enough Compositional Data Augmentationcited by 158
  3. 2017Dataset Augmentation in Feature Spacecited by 124
  4. 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
  5. 2016Edinburgh Neural Machine Translation Systems for WMT 16cited by 76
  6. 2021Tailor: Generating and Perturbing Text with Semantic Controlscited by 68
  7. 2021Neural Data Augmentation via Example Extrapolationcited by 54
  8. 2020Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generationcited by 47
  9. 2019A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classificationcited by 45
  10. 2020How Effective is Task-Agnostic Data Augmentation for Pretrained Transformers?cited by 41
  11. 2017Towards Zero-Shot Frame Semantic Parsing for Domain Scalingcited by 40
  12. 2021Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learningcited by 35
  13. 2020Nurse is Closer to Woman than Surgeon? Mitigating Gender-Biased Proximities in Word Embeddingscited by 20

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 1; 2025: 1.

5 papers.

  1. 2022A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processingcited by 21
  2. 2025PrePrompt: Predictive prompting for class incremental learningcited by 3
  3. 2022Reprint: a randomized extrapolation based on principal components for data augmentationcited by 1
  4. 2023Deep Metric Learning Assisted by Intra-variance in A Semi-supervised View of Learningcited by 0
  5. 2024Enhancing Personality Recognition in Dialogue by Data Augmentation and Heterogeneous Conversational Graph Networkscited by 0