deletions | additions       diff --git a/bf_Abstract_The_word2vec_software__.tex b/bf_Abstract_The_word2vec_software__.tex  index 7ee8da9..3200b0c 100644  --- a/bf_Abstract_The_word2vec_software__.tex  +++ b/bf_Abstract_The_word2vec_software__.tex 
...
{\bf Abstract}  The goal of formalization, proposed in this paper, is to bring together,   as near as possible, the linguistic  problem of synonym conception and the computer linguistic methods based generally  on empirical intuitive unjustified  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 by T. Mikolov.  , obtained by means of the neural networks,   word embedding in euclidean space, em  The word2vec software of Tomas Mikolov and colleagues1 has gained a lot  of traction lately, and provides state-of-the-art word embeddings. The learning  models behind the software are described in two research papers [1, 2]. We 
...
figure out the rationale behind the equations.  We show how to consider similarity between  features for calculation of similarity of objects in the Vector Space Model (VSM) for machine learning algorithms and other classes of methods that involve similarity between objects. Unlike LSA, we assume that similarity between features is known (say, from a synonym dictionary) and does not need to be learned from the data.  We call the proposed similarity measure soft similarity.  Similarity between features is common, for example, in