This zip consists of two different lexical semantics evaluation datasets used in the article: 

Ugur Sopaoglu and Gonenc Ercan. Evaluation of Semantic Relatedness Measures for Turkish Language. In Proceedings of the 17th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing 2016), Konya, Turkey, 2016

The first file "semanticCategories.csv" contains the semantic categories translated from English. The task is to cluster the words using a semantic relatedness function and to get the original categories. The categories and the system clusters are evaluated using Clustering Purity. Check the article for details. 

The second file "wordPairs.csv" contains the word similarity task used in the same article. The file contains the judgement of all the human annotators, for each word pair. The algorithms should calculate the correlation of the system generated scores with the average human annotator scores.