Here you can download the hyponym generation dataset used for evaluation in the paper linked below. Each line contains a hypernym, followed by all or its hyponyms.
HyponymGen.zip : The main dataset
hypgen_candidates.zip : The list of words that were used as hyponym candidates in the experiments
If you use this dataset, please reference the following paper:
Looking for hyponyms in vector space In Proceedings of the Eighteenth Conference on Computational Natural Language Learning (CoNLL-14) Baltimore, Maryland, United States, 2014