SoftEDA: Rethinking Rule-Based Data Augmentation with Soft Labels
Rule-based text data augmentation is widely used for NLP tasks due to its simplicity. However, this method can potentially damage the original meaning of the text, ultimately hurting the performance of the model. To overcome this limitation, we propose a straightforward technique for applying soft labels to augmented data. We conducted experiments across seven different classification tasks and empirically demonstrated the effectiveness of our proposed approach. We have publicly opened our source code for reproducibility.
Code (1)
Tasks
Data AugmentationSimilar Papers 제목 키워드 기반
AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimes
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 po…
Data AugmentationRethinking Rotation in Self-Supervised Contrastive Learning: Adaptive Positive or Negative Data Augmentation
Rotation is frequently listed as a candidate for data augmentation in contrastive learning but seldom provides satisfactory improvements. We argue that this is because the rotated image is always treated as either positi…
Contrastive LearningData AugmentationRethinking Data Augmentation for Robust Visual Question Answering
Data Augmentation (DA) -- generating extra training samples beyond original training set -- has been widely-used in today's unbiased VQA models to mitigate the language biases. Current mainstream DA strategies are synthe…
Data AugmentationKnowledge DistillationQuestion AnsweringVisual Question Answering+1Simple Augmentations of Logical Rules for Neuro-Symbolic Knowledge Graph Completion
High-quality and high-coverage rule sets are imperative to the success of Neuro-Symbolic Knowledge Graph Completion (NS-KGC) models, because they form the basis of all symbolic inferences. Recent literature builds neural…
Knowledge Graph CompletionRethinking Soft Label in Label Distribution Learning Perspective
The primary goal of training in early convolutional neural networks (CNN) is the higher generalization performance of the model. However, as the expected calibration error (ECE), which quantifies the explanatory power of…
Data Augmentationimage-classificationImage Classification