MSMix:An Interpolation-Based Text Data Augmentation Method Manifold Swap Mixup
This work addresses data insufficiency for deep neural networks in Chinese intention recognition, but it is incremental as it builds on existing interpolation-based augmentation techniques.
The paper tackles the problem of poor performance in deep neural networks due to insufficient data by proposing MSMix, an interpolation-based data augmentation method that mixes hidden features from two samples at a random layer, achieving better results than other methods on three Chinese intention recognition datasets in both full-sample and small-sample configurations.
To solve the problem of poor performance of deep neural network models due to insufficient data, a simple yet effective interpolation-based data augmentation method is proposed: MSMix (Manifold Swap Mixup). This method feeds two different samples to the same deep neural network model, and then randomly select a specific layer and partially replace hidden features at that layer of one of the samples by the counterpart of the other. The mixed hidden features are fed to the model and go through the rest of the network. Two different selection strategies are also proposed to obtain richer hidden representation. Experiments are conducted on three Chinese intention recognition datasets, and the results show that the MSMix method achieves better results than other methods in both full-sample and small-sample configurations.