April 2020
Beginner to intermediate
216 pages
5h 23m
English

You can divide the main objects composing the spaCy API into two categories: containers (such as Tokens and Doc objects) and processing pipeline components (such as the part-of-speech tagger and named entity recognizer). This chapter explores container objects further. Using container objects and their methods, you can access the linguistic annotations that spaCy assigns to each token in a text.
You’ll also learn how to customize the pipeline components to suit your needs and use Cython code to speed up time-consuming NLP tasks.
A container object groups multiple elements ...