The application of the connectionist method of semantic similarity for Kazakh language

The unsupervised algorithm for the calculation of semantic similarity are essential in many areas of modern natural language processing. One of the most promising methods for the calculation of semantic similarity is neural network algorithm "word2vec. This method has been tested for most European languages, namely English, German, French and Russian. This paper presents the results of numerical experiments for synthetic agglutinative Kazakh language, which has a number of features and differences from all the above languages.