mlsanityData to 7 Oct 2026

Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations

arXiv 1805.06201 ↗First posted 16 May 2018cs.CL cs.LGcited by 201

Not on the map. Why?

Abstract (arXiv)

We propose a novel data augmentation for labeled sentences called contextual augmentation. We assume an invariance that sentences are natural even if the words in the sentences are replaced with other words with paradigmatic relations. We stochastically replace words with other words that are predicted by a bi-directional language model at the word positions. Words predicted according to a context are numerous but appropriate for the augmentation of the original words. Furthermore, we retrofit a language model with a label-conditional architecture, which allows the model to augment sentences without breaking the label-compatibility. Through the experiments for six various different text classification tasks, we demonstrate that the proposed method improves classifiers based on the convolutional or recurrent neural networks.

Key facts. Cited by 201 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 58; 2022: 49; 2023: 41; 2024: 35; 2025: 10; 2026: 8.

201 papers.

Sort:

By area:

  1. 2021A Survey of Data Augmentation Approaches for NLPcited by 408
  2. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 399
  3. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 358
  4. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 337
  5. 2023Physics of Language Models: Part 3.1, Knowledge Storage and Extractioncited by 264
  6. 2023Taken out of context: On measuring situational awareness in LLMscited by 131
  7. 2023AugGPT: Leveraging ChatGPT for Text Data Augmentationcited by 128
  8. 2021CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarizationcited by 120
  9. 2021A Survey on Data Augmentation for Text Classificationcited by 111
  10. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  11. 2023Waffling around for Performance: Visual Classification with Random Words and Broad Conceptscited by 100
  12. 2021Supporting Clustering with Contrastive Learningcited by 90
38 more
  1. 2021Data Augmentation Approaches in Natural Language Processing: A Surveycited by 82
  2. 2021Vision-Language Navigation with Random Environmental Mixupcited by 70
  3. 2021AEDA: An Easier Data Augmentation Technique for Text Classificationcited by 67
  4. 2022InPars: Data Augmentation for Information Retrieval using Large Language Modelscited by 60
  5. 2022RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extractioncited by 60
  6. 2021Generate, Annotate, and Learn: NLP with Synthetic Textcited by 42
  7. 2021MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NERcited by 42
  8. 2024A Survey on Data Synthesis and Augmentation for Large Language Modelscited by 40
  9. 2022Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learningcited by 38
  10. 2022DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptationcited by 36
  11. 2021Prevent the Language Model from being Overconfident in Neural Machine Translationcited by 34
  12. 2021Gradient Imitation Reinforcement Learning for Low Resource Relation Extractioncited by 33
  13. 2021FlipDA: Effective and Robust Data Augmentation for Few-Shot Learningcited by 32
  14. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
  15. 2023Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matchingcited by 30
  16. 2021Substructure Substitution: Structured Data Augmentation for NLPcited by 25
  17. 2021Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifierscited by 24
  18. 2023Mixture of Soft Prompts for Controllable Data Generationcited by 23
  19. 2021Virtual Augmentation Supported Contrastive Learning of Sentence Representationscited by 21
  20. 2021GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentationcited by 20
  21. 2021Rethinking Perturbations in Encoder-Decoders for Fast Trainingcited by 17
  22. 2021Interpreting the Robustness of Neural NLP Models to Textual Perturbationscited by 17
  23. 2022Learning Multimodal Data Augmentation in Feature Spacecited by 17
  24. 2021Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systemscited by 16
  25. 2021Text AutoAugment: Learning Compositional Augmentation Policy for Text Classificationcited by 15
  26. 2022TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understandingcited by 15
  27. 2021Phrase-level Active Learning for Neural Machine Translationcited by 13
  28. 2022Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Taskscited by 13
  29. 2022Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translationcited by 13
  30. 2023Exploring Multimodal Approaches for Alzheimer's Disease Detection Using Patient Speech Transcript and Audio Datacited by 13
  31. 2021To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLPcited by 12
  32. 2022A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysiscited by 12
  33. 2021Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networkscited by 11
  34. 2022Improving Short Text Classification With Augmented Data Using GPT-3cited by 11
  35. 2022Conditional Supervised Contrastive Learning for Fair Text Classificationcited by 11
  36. 2023Model-Agnostic Meta-Learning for Multilingual Hate Speech Detectioncited by 11
  37. 2024Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learningcited by 11
  38. 2021Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMaxcited by 10

50 most cited of 201 All 201 (JSON)