The issue of shortcut learning is widely known in NLP and has been an
important research focus in recent years. Unintended correlations in the data
enable models to easily solve tasks that were meant to exhibit advanced
language understanding and reasoning capabilities. In this survey paper, we
focus on the field of machine reading comprehension (MRC), an important task
for showcasing high-level language understanding that also suffers from a range
of shortcuts. We summarize the available techniques for measuring and
mitigating shortcuts and conclude with suggestions for further progress in
shortcut research. Most importantly, we highlight two main concerns for
shortcut mitigation in MRC: the lack of public challenge sets, a necessary
component for effective and reusable evaluation, and the lack of certain
mitigation techniques that are prominent in other areas.

本综述论文探讨了自然语言处理中普遍存在的快捷学习问题，侧重于机器阅读理解领域，总结了已有的快捷学习测量和减轻方法，并提出了缺乏公共挑战集合和其他领域突出的快捷学习方法对 MRC 的两个主要关注点。