长尾类分布下多标签文本分类的平衡方法
Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution
摘要：
多标签文本分类是一项具有挑战性的任务，因为它需要捕获标签依赖性。当类分布是长尾分布时，它变得更具挑战性。恢复和重新加权是用于解决类不平衡问题的常用方法，然而，当除了类不平衡之外还存在标签依赖时，它们是无效的，因为它们导致对公共标签的过采样。本文介绍了平衡损失函数在多标签文本分类中的应用。我们在一个有90个标签的一般域数据集（路透社-21578）和一个有18211个标签的PubMed域特定数据集上进行实验。我们发现，一个分布平衡的损失函数，它本质上解决了类的不平衡和标签链接的问题，优于常用的损失函数。分布均衡方法已成功地应用于图像识别领域。在这里，我们展示了它们在自然语言处理中的有效性。源代码可在https://github.com/Roche/BalancedLossNLP上获得。
英文摘要：
Multi-label text classification is a challenging task because it requires capturing label dependencies. It becomes even more challenging when class distribution is long-tailed. Resampling and re-weighting are common approaches used for addressing the class imbalance problem, however, they are not effective when there is label dependency besides class imbalance because they result in oversampling of common labels. Here, we introduce the application of balancing loss functions for multi-label text classification. We perform experiments on a general domain dataset with 90 labels (Reuters-21578) and a domain-specific dataset from PubMed with 18211 labels. We find that a distribution-balanced loss function, which inherently addresses both the class imbalance and label linkage problems, outperforms commonly used loss functions. Distribution balancing methods have been successfully used in the image recognition field. Here, we show their effectiveness in natural language processing. Source code is available at https://github.com/Roche/BalancedLossNLP.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
