Summary

In this chapter, you worked with word vectors, which are floating-point vectors that represent word semantics. First, you learned about the different ways to perform text vectorization, as well as how to use word vectors and distributed semantics. Then, you explored the vector operations that word vectors allow and what semantics these operations bring.

You also learned how to use spaCy's built-in word vectors and how to import third-party vectors into spaCy. Finally, you learned about vector-based semantic similarity and how to blend linguistic concepts with word vectors to get the best out of these semantics.

The next chapter is full of surprises – we'll look at a real-word case-based study that allows you to blend what you've learned about in the past five chapters. Let's see what spaCy can do when it comes to real-world problems!