Abstract
In real-world text classification tasks, negative texts often contain a minimal proportion of negative content, which is especially problematic in areas like text quality control, legal risk screening, and sensitive information interception. This challenge manifests at two levels: at the macro level, distinguishing negative texts is difficult due to the high similarity between coarse-grained positive and negative samples; at the micro level, the issue stems from extreme class imbalance and a lack of fine-grained labels. To address these challenges, we propose transforming the coarse-grained positive-negative (PN) classification task into an imbalanced fine-grained positive-unlabeled (PU) classification problem, supported by theoretical analysis. We introduce a novel framework, Balanced Fine-Grained Positive-Unlabeled (BFGPU) learning, which features a unique PU learning loss function that optimizes macro-level performance amidst severe imbalance at the micro level. The framework's performance is further boosted by rebalanced pseudo-labeling and threshold adjustment. Extensive experiments on both public and real-world datasets demonstrate the effectiveness of BFGPU, which outperforms other methods, even in extreme scenarios where both macro and micro levels are highly imbalanced.
Abstract (translated)
在实际文本分类任务中，负面文本往往只包含少量的负面内容，在诸如文本质量控制、法律风险筛查和敏感信息拦截等领域的应用尤其成问题。这一挑战体现在两个层面：宏观层面上，由于粗粒度正负样本之间的高度相似性，区分负面文本变得困难；微观层面上，则是由极端类别不平衡以及缺乏细粒度标签所导致的问题。为解决这些挑战，我们提出将粗粒度的正负（PN）分类任务转换为不平衡的细粒度正未标记（PU）分类问题，并通过理论分析加以支持。为此，我们引入了一种全新的框架——平衡细粒度正未标记（BFGPU）学习，该框架采用一种独特的PU学习损失函数，在微观层面上面对极端不平衡的情况下优化宏观层面的表现。此外，框架的性能还得到了重置伪标签和阈值调整技术的支持。在公共数据集及真实世界数据集上的广泛实验显示，BFGPU方法表现出色，并且即使是在极度失衡（无论是宏观层面还是微观层面）的情境下，它依然优于其他所有方法。
URL
https://arxiv.org/abs/2503.13562
