Weakly supervised text classification framework for noisy-labeled imbalanced samples

Wenxin Zhang, Yaya Zhou, Shuhui Liu, Yupei Zhang, Xuequn Shang

Abstract: Highlights•This study provides a solution to the problem of imbalanced text classification with noisy labels.•The proposed WeStcoin is to learn a noisy pattern and a clean pattern for classification.•WeStcoin extracts the misleading seed-words for an explanation on incorrect labels.