Word embedding allows us to memorize both the semantic and syntactic information of words, starting with an unknown corpus and constructing a vector space in which the vectors of words are closer if the words occur in the same linguistic contexts, that is, if they are recognized as semantically similar. Word2Vec is a set of templates that are used to produce word embedding; the package was originally created in C by Tomas Mikolov, and was then implemented in Python and Java.
Word2Vec using gensim
Getting ready
In this recipe, we will use the gensim library to build a Word2Vec model.
