SherLIiC

该数据集是一个针对上下文中的词汇推理的基准测试，主要关注谓词蕴含问题，并且大部分示例为负例。该数据集被用于在预训练语言模型（PLM）的背景下评估连续模式，同时提供了具体的训练细节。在规模上，该数据集的训练集较小，其中负例占比为67%，其任务是上下文中的词汇推理（Liic）。

This dataset is a benchmark for lexical inference in context, focusing primarily on predicate entailment problems, with most examples being negative instances. It is utilized to evaluate continuous patterns under the context of pre-trained language models (PLMs), while offering specific training details. In terms of scale, the training set is relatively small, with negative instances accounting for 67% of the total, and its targeted task is lexical inference in context (Liic).