Unsupervised Reinforcement Adaptation for Class-Imbalanced Text Classification
This addresses domain adaptation for text classification with imbalanced classes, which is an incremental improvement over existing methods focused on balanced data.
The paper tackles the problem of class imbalance in unsupervised domain adaptation for text classification by proposing a reinforcement learning approach that leverages feature variants and imbalanced labels across domains, achieving effective adaptation on three datasets.
Class imbalance naturally exists when train and test models in different domains. Unsupervised domain adaptation (UDA) augments model performance with only accessible annotations from the source domain and unlabeled data from the target domain. However, existing state-of-the-art UDA models learn domain-invariant representations and evaluate primarily on class-balanced data across domains. In this work, we propose an unsupervised domain adaptation approach via reinforcement learning that jointly leverages feature variants and imbalanced labels across domains. We experiment with the text classification task for its easily accessible datasets and compare the proposed method with five baselines. Experiments on three datasets prove that our proposed method can effectively learn robust domain-invariant representations and successfully adapt text classifiers on imbalanced classes over domains. The code is available at https://github.com/woqingdoua/ImbalanceClass.