Data augmentation is widely used in text classification, especially in the low-resource regime where a few examples for each class are available during training. Despite the success, generating data augmentations as hard positive examples that may increase their effectiveness is under-explored. This paper proposes an Adversarial Word Dilution (AWD) method that can generate hard positive examples as text data augmentations to train the low-resource text classification model efficiently. Our idea of augmenting the text data is to dilute the embedding of strong positive words by weighted mixing with unknown-word embedding, making the augmented inputs hard to be recognized as positive by the classification model. We adversarially learn the dilution weights through a constrained min-max optimization process with the guidance of the labels. Empirical studies on three benchmark datasets show that AWD can generate more effective data augmentations and outperform the state-of-the-art text data augmentation methods. The additional analysis demonstrates that the data augmentations generated by AWD are interpretable and can flexibly extend to new examples without further training.

翻译：数据增强广泛应用于文本分类任务，尤其在低资源场景下（每个类别仅含少量训练样本）尤为关键。尽管取得显著成效，但生成可提升模型效用的硬性正例数据增强方法仍鲜有探索。本文提出一种对抗性词汇稀释（AWD）方法，该方法能够生成作为文本数据增强的硬性正例，从而高效训练低资源文本分类模型。我们的数据增强核心思想是：通过将强正面词汇的嵌入与未知词嵌入进行加权混合来稀释其表征，使增强后的输入难以被分类模型识别为正例。我们借助标签的引导，通过约束极小极大优化过程对抗性地学习稀释权重。在三个基准数据集上的实验表明，AWD能生成更有效的数据增强样本，并超越现有最先进的文本数据增强方法。进一步分析证实，AWD生成的数据增强样本具有可解释性，且无需额外训练即可灵活扩展至新样本。