Many natural language processing (NLP) tasks are naturally imbalanced, as some target categories occur much more frequently than others in the real world. In such scenarios, current NLP models still tend to perform poorly on less frequent classes. Addressing class imbalance in NLP is an active research topic, yet, finding a good approach for a particular task and imbalance scenario is difficult. With this survey, the first overview on class imbalance in deep-learning based NLP, we provide guidance for NLP researchers and practitioners dealing with imbalanced data. We first discuss various types of controlled and real-world class imbalance. Our survey then covers approaches that have been explicitly proposed for class-imbalanced NLP tasks or, originating in the computer vision community, have been evaluated on them. We organize the methods by whether they are based on sampling, data augmentation, choice of loss function, staged learning, or model design. Finally, we discuss open problems such as dealing with multi-label scenarios, and propose systematic benchmarking and reporting in order to move forward on this problem as a community.

翻译：许多自然语言处理（NLP）任务天然存在不平衡性，因为现实世界中某些目标类别的出现频率远高于其他类别。在此类场景下，当前的NLP模型在低频类别上的表现仍不尽如人意。解决NLP中的类别不平衡问题是一个活跃的研究方向，然而针对特定任务与不平衡场景找到合适的方法却颇为困难。本综述作为首篇聚焦于基于深度学习的NLP中类别不平衡问题的概述性文献，旨在为处理不平衡数据的NLP研究者与从业人员提供指导。我们首先探讨了多种受控环境及真实场景下的类别不平衡类型。随后，本综述涵盖了针对类别不平衡NLP任务明确提出的方法，或源自计算机视觉领域并已在上述任务中得到评估的技术。我们依据这些方法是否基于采样、数据增强、损失函数选择、分阶段学习或模型设计对其进行分类。最后，我们讨论了多标签场景处理等开放性问题，并提出了系统性基准测试与报告机制，以期推动学术界共同解决这一难题。