Word2vec from Scratch with NumPy – Towards Data Science

Recently, I have been working with several projects related to NLP at work. Some of them had something to do with training the company's in-house word embedding. At work, the tasks were mostly done with the help of a Python library: gensim. However, I decided to implement a Word2vec model from scratch just with the help of Python and NumPy because reinventing the wheel is usually an awesome way to learn something deeply. Word embedding is nothing fancy but methods to represent words in a numerical way.