2025.emnlp-main.658@ACL

Total: 1

#1 Calibrating Pseudo-Labeling with Class Distribution for Semi-supervised Text Classification [PDF] [Copy] [Kimi] [REL]

Authors: Weiyi Yang, Richong Zhang, Junfan Chen, Jiawei Sheng

Semi-supervised text classification (SSTC) aims to train text classification models with few labeled data and massive unlabeled data. Existing studies develop effective pseudo-labeling methods, but they can struggle with unlabeled data that have imbalanced classes mismatched with the labeled data, making the pseudo-labeling biased towards majority classes, resulting in catastrophic error propagation. We believe it is crucial to explicitly estimate the overall class distribution, and use it to calibrate pseudo-labeling to constrain majority classes. To this end, we formulate the pseudo-labeling as an optimal transport (OT) problem, which transports the unlabeled sample distribution to the class distribution. With a memory bank, we dynamically collect both the high-confidence pseudo-labeled data and true labeled data, thus deriving reliable (pseudo-) labels for class distribution estimation. Empirical results on 3 commonly used benchmarks demonstrate that our model is effective and outperforms previous state-of-the-art methods.

Subject: EMNLP.2025 - Main