Understanding the logic of the word2vec model

We will start decomposing the word2vec model and try to understand the logic of it. word2vec is a piece of software and it uses a bunch of algorithms. Refer to Figure 6.7:

Figure 6.7: Word2vec building block (Image credit: Xin Rong)

As you can see in Figure 6.7, there are three main building blocks. We will examine each of them in detail:

• Vocabulary builder
• Context builder
• Neural network with two layers

Vocabulary builder

The vocabulary builder is the first building block of the word2vec model. It takes raw text data, mostly in the form of sentences. The vocabulary builder is used to build vocabulary from your given text corpus. It will collect all the unique words from your...