Problem $1.$ Word Embedding Problem

Generate word embedding from your favorite story or article $($it should be very large in size$).$ Use Word$2$Vec algorithm for word embedding. You can either use CBOW architecture or Skip Gram architecture. Choose ten pairs of words from the story or article. Find the cosine similarity between those pairs of words. Which pair of words has the highest similarity?

$[$Hints: you can use Natural Language Toolkit $($nltk$)$ in Python for tokenizing

pip install nltk

you can use Python Gensim library for training Word$2$Vec model pip install genism$]$