Semi-supervised text classification (SSTC) has gained increasing attention
due to its ability to leverage unlabeled data. However, existing approaches
based on pseudo-labeling suffer from the issues of pseudo-label bias and error
accumulation. In this paper, we propose JointMatch, a holistic approach for
SSTC that addresses these challenges by unifying ideas from recent
semi-supervised learning and the task of learning with noise. JointMatch
adaptively adjusts classwise thresholds based on the learning status of
different classes to mitigate model bias towards current easy classes.
Additionally, JointMatch alleviates error accumulation by utilizing two
differently initialized networks to teach each other in a cross-labeling
manner. To maintain divergence between the two networks for mutual learning, we
introduce a strategy that weighs more disagreement data while also allowing the
utilization of high-quality agreement data for training. Experimental results
on benchmark datasets demonstrate the superior performance of JointMatch,
achieving a significant 5.13% improvement on average. Notably, JointMatch
delivers impressive results even in the extremely-scarce-label setting,
obtaining 86% accuracy on AG News with only 5 labels per class. We make our
code available at this https URL

提出了一种名为 JointMatch 的新方法，用于半监督文本分类，通过结合最近半监督学习和学习带有噪声任务的理念，解决了伪标签偏见和错误积累的问题。JointMatch 通过根据不同类别的学习状态自适应调整类别阈值，减轻了模型对当前容易类别的偏见。此外，JointMatch 通过利用两个初始化不同的网络以交互标记的方式互相教导，减轻了错误的积累问题。实验结果表明，JointMatch 在基准数据集上表现优越，在平均上提高了 5.13% 的性能。“尤其值得注意的是，即使在极度稀缺标签的情况下，JointMatch 在 AG News 上的准确率达到了 86%，每个类别仅有 5 个标签。我们将我们的代码发布在此 https URL。