重访预训练语言模型的 k-NN（英文版）

英文标题：Revisiting k-NN for Pre-trained Language Models中文摘要：本文介绍了如何将 k - 最近邻分类器与预训练语言模型相结合以提高自然语言处理的效率，具体方法是采用 k - 最近邻分类器对预训练语言模型进行文本表示，通过校准训练过程来掌握具体实例的困难度，并将校准结果与预训练语言模型的分类器相结合。英文摘要：Pre-trained Language Models (PLMs), as parametric-based eager learners, havebecome the de-facto choice for current paradigms of Natural Language Processing(NLP). In contrast, k-Nearest-Neighbor (k-NN) classifiers, as the lazy learningparadigm, tend to mitigate over-fitting and isolated noise. In this paper, werevisit k