AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimes
Not on the map. Why?
Abstract (arXiv)
Text data augmentation is a complex problem due to the discrete nature of sentences. Although rule-based augmentation methods are widely adopted in real-world applications because of their simplicity, they suffer from potential semantic damage. Previous researchers have suggested easy data augmentation with soft labels (softEDA), employing label smoothing to mitigate this problem. However, finding the best factor for each model and dataset is challenging; therefore, using softEDA in real-world applications is still difficult. In this paper, we propose adapting AutoAugment to solve this problem. The experimental results suggest that the proposed method can boost existing augmentation methods and that rule-based methods can enhance cutting-edge pre-trained language models. We offer the source code.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 31 of its 52 references that are in the map. First posted on arXiv 8 Feb 2024.
Builds on
31 of 52 references.
References · 31
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
- 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
- 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
- 2018Neural Network Acceptability Judgmentscited by 952
- 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
- 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
19 more
- 2021A Survey of Data Augmentation Approaches for NLPcited by 408
- 2018Tune: A Research Platform for Distributed Model Selection and Trainingcited by 395
- 2017Synthetic and Natural Noise Both Break Neural Machine Translationcited by 304
- 2021GPT3Mix: Leveraging Large-scale Language Models for Text Augmentationcited by 185
- 2019Not Enough Data? Deep Learning to the Rescue!cited by 174
- 2023AugGPT: Leveraging ChatGPT for Text Data Augmentationcited by 128
- 2021A Survey on Data Augmentation for Text Classificationcited by 111
- 2018Conditional BERT Contextual Augmentationcited by 107
- 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
- 2021Data Augmentation Approaches in Natural Language Processing: A Surveycited by 82
- 2021AEDA: An Easier Data Augmentation Technique for Text Classificationcited by 67
- 2018Data augmentation instead of explicit regularizationcited by 62
- 2019Learning Data Manipulation for Augmentation and Weightingcited by 44
- 2020How Effective is Task-Agnostic Data Augmentation for Pretrained Transformers?cited by 41
- 2021SSMix: Saliency-Based Span Mixup for Text Classificationcited by 39
- 2019Improving short text classification through global augmentation methodscited by 33
- 2021Text AutoAugment: Learning Compositional Augmentation Policy for Text Classificationcited by 15
- 2022EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text Classificationcited by 7
- 2021LINDA: Unsupervised Learning to Interpolate in Natural Language Processingcited by 6
Built on by
Citing papers per year: 2025: 1.
1 paper.