arXiv 2202.025662022-02-05cs.CL

LST：面向Few-Shot文本分类的词典引导自训练算法

LST: Lexicon-Guided Self-Training for Few-Shot Text Classification

Yonsei University（延世大学）

Hazel Kim, Jaeman Son, Yo-Sub Han

摘要：

自训练提供了一种有效的方法，可以使用极少量的标记数据为未标记数据创建伪标签。许多最先进的自训练方法都依赖于不同的正则化方法来防止过拟合和提高泛化能力。然而，它们仍然严重依赖于最初用有限的标记数据作为伪标签训练的预测，并且可能会根据第一次预测将过度自信的标签信念放在错误的类别上。为了解决文本分类中的这个问题，我们引入了LST，这是一种简单的自训练方法，它使用词典以丰富的语言方式指导伪标签机制。我们通过预测看不见的数据的置信度来不断改进词典，以便在训练迭代中更好地教授伪标签。我们证明，这种简单而精心制作的词汇知识实现了1.0-2.0%的性能比目前最先进的方法，每类30个标记的样本的五个基准数据集。

英文摘要：

Self-training provides an effective means of using an extremely small amount of labeled data to create pseudo-labels for unlabeled data. Many state-of-the-art self-training approaches hinge on different regularization methods to prevent overfitting and improve generalization. Yet they still rely heavily on predictions initially trained with the limited labeled data as pseudo-labels and are likely to put overconfident label belief on erroneous classes depending on the first prediction. To tackle this issue in text classification, we introduce LST, a simple self-training method that uses a lexicon to guide the pseudo-labeling mechanism in a linguistically-enriched manner. We consistently refine the lexicon by predicting confidence of the unseen data to teach pseudo-labels better in the training iterations. We demonstrate that this simple yet well-crafted lexical knowledge achieves 1.0-2.0% better performance on 30 labeled samples per class for five benchmark datasets than the current state-of-the-art approaches.

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。

摘要：

英文摘要：

相关论文