deletions | additions       diff --git a/bf_Abstract_The_goal_of__.tex b/bf_Abstract_The_goal_of__.tex  index 3200b0c..70b1ca1 100644  --- a/bf_Abstract_The_goal_of__.tex  +++ b/bf_Abstract_The_goal_of__.tex 
...
factors. Using the word vector representation we have proposed the geometric   approach to mathematical modeling of synset.  The word embedding is based on the neural networks (Skip-gram, CBOW),   developed and realized as word2vec programme program  by T. Mikolov. The standard cosine similarity is used as the distance between word-vectors.  Several geometric characteristics of the synset words are introduced: the interior of synset,  the synset word rank and centrality. These notions are intended to select the most significant synset words, i.e. the words   which senses are the nearest ones to the sense of a synset.  Some experiments with proposed notions, based on Rusvectores resources, are represented.