Contrastive Learning has emerged as a powerful representation learning method and facilitates various downstream tasks especially when supervised data is limited. How to construct efficient contrastive samples through data augmentation is key to its success. Unlike vision tasks, the data augmentation method for contrastive learning has not been investigated sufficiently in language tasks. In this paper, we propose a novel approach to construct contrastive samples for language tasks using text summarization. We use these samples for supervised contrastive learning to gain better text representations which greatly benefit text classification tasks with limited annotations. To further improve the method, we mix up samples from different classes and add an extra regularization, named Mixsum, in addition to the cross-entropy-loss. Experiments on real-world text classification datasets (Amazon-5, Yelp-5, AG News, and IMDb) demonstrate the effectiveness of the proposed contrastive learning framework with summarization-based data augmentation and Mixsum regularization.
翻译:对比学习已成为一种强大的代表性学习方法,有利于各种下游任务,特别是在受监督的数据有限的情况下。如何通过数据增强建立高效对比样本是成功的关键。与愿景任务不同,对比学习的数据增强方法在语言任务中没有得到充分调查。在本文件中,我们提出一种新颖的方法,用文本归纳方法为语言任务构建对比样本。我们利用这些样本进行监督对比学习,以获得更好的文本表述,从而在有限的说明下大大有利于文本分类任务。为了进一步改进这一方法,我们将不同类别的样本混合起来,并加上一个额外的正规化,即称为Mixsum,以及交叉的有机损失。关于真实世界文本分类数据集(Amazon-5、Yelp-5、AG News和IMDb)的实验展示了拟议对比学习框架的有效性,其基于合成的数据增强和混合规范。