Learning word vectors

To implement a fully functional word embedding model, we will perform the following steps:

1. Loading all the dependencies
2. Preparing the text corpus

3. Defining the model
4. Training the model
5. Analyzing the model
6. Plotting the word cluster using the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm
7. Plotting the model on TensorBoard

Let's make some world-class word embedding models!

The code for this section is available at https://github.com/PacktPublishing/Python-Deep-Learning-Projects/blob/master/Chapter03/create_word2vec.ipynb.

Loading all the dependencies

In this chapter, we will be using the gensim module (https://github.com/RaRe-Technologies/gensim) to train our word2vec model. Gensim...