paper-with-me

Papers

SoftEDA: Rethinking Rule-Based Data Augmentation with Soft Labels

2024-02-08 · Juhwan Choi, Kyohoon Jin, Junho Lee, Sangmin Song, Youngbin Kim

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.

📄 PDF Abstract BibTeX arXiv:2402.05591

Code (1)

c-juhwan/softeda 공식 구현 pytorch

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimes

2024-02-08 · Juhwan Choi, Kyohoon Jin, Junho Lee, Sangmin Song 외

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 Augmentation

Rethinking Rotation in Self-Supervised Contrastive Learning: Adaptive Positive or Negative Data Augmentation

2022-10-23 · Atsuyuki Miyai, Qing Yu, Daiki Ikami, Go Irie 외

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 Augmentation

Rethinking Data Augmentation for Robust Visual Question Answering

2022-07-18 · Long Chen, Yuhang Zheng, Jun Xiao

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+1

Simple Augmentations of Logical Rules for Neuro-Symbolic Knowledge Graph Completion

2024-07-02 · Ananjan Nandi, Navdeep Kaur, Parag Singla, Mausam

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 Completion

Rethinking Soft Label in Label Distribution Learning Perspective

2023-01-31 · Seungbum Hong, Jihun Yoon, Bogyu Park, Min-Kook Choi

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