DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification

by   Hui Chen, et al.
Georgia Institute of Technology
Singapore University of Technology and Design

This paper proposes a simple yet effective interpolation-based data augmentation approach termed DoubleMix, to improve the robustness of models in text classification. DoubleMix first leverages a couple of simple augmentation operations to generate several perturbed samples for each training data, and then uses the perturbed data and original data to carry out a two-step interpolation in the hidden space of neural models. Concretely, it first mixes up the perturbed data to a synthetic sample and then mixes up the original data and the synthetic perturbed data. DoubleMix enhances models' robustness by learning the "shifted" features in hidden space. On six text classification benchmark datasets, our approach outperforms several popular text augmentation methods including token-level, sentence-level, and hidden-level data augmentation techniques. Also, experiments in low-resource settings show our approach consistently improves models' performance when the training data is scarce. Extensive ablation studies and case studies confirm that each component of our approach contributes to the final performance and show that our approach exhibits superior performance on challenging counterexamples. Additionally, visual analysis shows that text features generated by our approach are highly interpretable. Our code for this paper can be found at


page 1

page 2

page 3

page 4


Good-Enough Example Extrapolation

This paper asks whether extrapolating the hidden space distribution of t...

MSMix:An Interpolation-Based Text Data Augmentation Method Manifold Swap Mixup

To solve the problem of poor performance of deep neural network models d...

Pseudo-labelling Enhanced Media Bias Detection

Leveraging unlabelled data through weak or distant supervision is a comp...

Feature Weaken: Vicinal Data Augmentation for Classification

Deep learning usually relies on training large-scale data samples to ach...

Low Resource Text Classification with ULMFit and Backtranslation

In computer vision, virtually every state of the art deep learning syste...

Reprint: a randomized extrapolation based on principal components for data augmentation

Data scarcity and data imbalance have attracted a lot of attention in ma...

Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations

A limited amount of studies investigates the role of model-agnostic adve...

Please sign up or login with your details

Forgot password? Click here to reset