It isn't a coincidence that every time we mentioned actually performing POS-tagging, we linked to or mentioned spaCy – it is arguably one of the fastest tokenizer, tagger, and parser out there, and we will be using it for all our examples.

But before we dive into spaCy, we will be briefly discussing its main rival when it comes to POS-tagging in Python, which is NLTK. We have already gone through the spaCy versus NLTK debate before, and we will stick to our previous stance of using spaCy for all our real-world application purposes, but it is still worth looking at what NLTK has to offer.

NLTK's fairly straightforward API for playing around or sandboxing is what usually tends to make it an attractive choice for beginners. To get the appropriate tags for a sentence, all we have to run is this:

import nltk
text = nltk.word_tokenize("And...