paper-with-me

홈 › Papers

Augmenting Data with Mixup for Sentence Classification: An Empirical Study

2019-05-22 · Hongyu Guo, Yongyi Mao, Richong Zhang

Mixup, a recent proposed data augmentation method through linearly interpolating inputs and modeling targets of random samples, has demonstrated its capability of significantly improving the predictive accuracy of the state-of-the-art networks for image classification. However, how this technique can be applied to and what is its effectiveness on natural language processing (NLP) tasks have not been investigated. In this paper, we propose two strategies for the adaption of Mixup on sentence classification: one performs interpolation on word embeddings and another on sentence embeddings. We conduct experiments to evaluate our methods using several benchmark datasets. Our studies show that such interpolation strategies serve as an effective, domain independent data augmentation approach for sentence classification, and can result in significant accuracy improvement for both CNN and LSTM models.

📄 PDF Abstract BibTeX arXiv:1905.08941

Code (3)

dsfsi/textaugment tf
xashru/mixup-text pytorch
ziegler-ingo/cleavage_prediction pytorch

Tasks

ClassificationData AugmentationGeneral Classificationimage-classificationImage ClassificationSentenceSentence ClassificationSentence EmbeddingsWord Embeddings

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Mixup Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels:…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

SSMix: Saliency-Based Span Mixup for Text Classification

2021-06-15 · Findings (ACL) 2021 8 · Soyoung Yoon, Gyuwan Kim, Kyumin Park

Data augmentation with mixup has shown to be effective on various computer vision tasks. Despite its great success, there has been a hurdle to apply mixup to NLP tasks since text consists of discrete tokens with variable…

ClassificationData AugmentationNatural Language InferenceSentence+4

Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup

2023-05-26 · Damien Teney, Jindong Wang, Ehsan Abbasnejad

Mixup is a highly successful technique to improve generalization of neural networks by augmenting the training data with combinations of random pairs. Selective mixup is a family of methods that apply mixup to specific p…

Binary Classification

DMix: Distance Constrained Interpolative Mixup

2021-11-01 · EMNLP (MRL) 2021 11 · Ramit Sawhney, Megh Thakkar, Shrey Pandit, Debdoot Mukherjee 외

Interpolation-based regularisation methods have proven to be effective for various tasks and modalities. Mixup is a data augmentation method that generates virtual training samples from convex combinations of individual …

ClassificationData AugmentationSentenceSentence Classification

Towards Understanding the Data Dependency of Mixup-style Training

2021-10-14 · ICLR 2022 4 · Muthu Chidambaram, Xiang Wang, Yuzheng Hu, Chenwei Wu 외

In the Mixup training paradigm, a model is trained using convex combinations of data points and their associated labels. Despite seeing very few true data points during training, models trained using Mixup seem to still …

LINDA: Unsupervised Learning to Interpolate in Natural Language Processing

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Despite the success of mixup in data augmentation, its applicability to natural language processing (NLP) tasks has been limited due to the discrete and variable-length nature of natural languages. Recent studies have th…

Data Augmentationtext-classificationText Classification