neural networks; lemma; context specificity; Word Embeddings

The study deals with the application of the neural networks in the linguisticresearch of word semantics. A new method of measuring context specificity oflemma based on Word Embeddings Word2vec technique is proposed in thefirst part of the article. Then the method is illustrated in the analysis of theCzech political discourse in the second part. The research is based on thecorpus of the Czech journalism consisting of more than 3 billion tokens. Theresults show that the proposed method is applicable for detecting the semanticdevelopment of a lemma and it could have a great potential for linguisticstudies if one can apply it with comprehensive explanations.