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：数据增强在文本分类中广泛应用，尤其是在低资源场景下（即训练时每个类别仅有少量样本可用）。尽管取得了成功，但生成能提升模型效果的困难正例数据增强方法尚待深入探索。本文提出一种敌对词稀释（Adversarial Word Dilution, AWD）方法，可生成作为文本数据增强的困难正例，从而高效训练低资源文本分类模型。我们的文本数据增强思路是：通过将强积极词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积极样本。我们通过约束极小极大优化过程，在标签引导下对抗性地学习稀释权重。在三个基准数据集上的实证研究表明，AWD能生成更有效的数据增强样本，并优于当前最先进的文本数据增强方法。进一步分析表明，AWD生成的数据增强具有可解释性，且无需额外训练即可灵活扩展至新样本。