Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation
This work addresses a practical problem for researchers and practitioners in supervised learning by offering an incremental improvement in text classification methods.
The paper tackles the challenge of adapting contrastive learning to supervised tasks by introducing a dual contrastive learning framework that learns input features and classifier parameters simultaneously, resulting in improved classification accuracy on benchmark text datasets.
Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in practice. In this work, we introduce a dual contrastive learning (DualCL) framework that simultaneously learns the features of input samples and the parameters of classifiers in the same space. Specifically, DualCL regards the parameters of the classifiers as augmented samples associating to different labels and then exploits the contrastive learning between the input samples and the augmented samples. Empirical studies on five benchmark text classification datasets and their low-resource version demonstrate the improvement in classification accuracy and confirm the capability of learning discriminative representations of DualCL.