EVALution

该数据集被用于评估上位词检测方法的性能。此外，对于某些关系，其表现不如最佳测量结果。该数据集所涉及的任务是上位词检测。

This dataset is utilized to evaluate the performance of hypernym detection methods. Furthermore, for certain relations, the performance of these methods falls short of the optimal measured results. The task addressed by this dataset is hypernym detection.