SemEval-2018 Task-9

该数据集专为医学领域设计，包含了大量的下义词及其对应的上级词列表。数据集被平等地划分为训练集和测试集，其中试验数据作为验证集。在测试集的金标准中，包含了4,116组下义词-上级词对。该数据集的任务是进行上级词的发现。

This dataset is specifically designed for the medical domain, containing a large number of hyponyms and their corresponding hypernym lists. The dataset is equally divided into a training set and a test set, with the experimental data serving as the validation set. The gold standard of the test set includes 4,116 hyponym-hypernym pairs. The task of this dataset is hypernym discovery.