As you learned in Chapter 1, spaCy contains statistical neural network models trained to perform named entity recognition, part-of-speech tagging, syntactic dependency parsing, and semantic similarity prediction. But you’re not limited to using only pretrained, ready-to-use models. You can also train a model with your own training examples, tuning its pipeline components for your application’s requirements.

This chapter covers how to train spaCy’s named entity recognizer and dependency parser, the pipeline components that you most often need to customize to make the model you’re using specific to a particular use case. The reason ...

Get Natural Language Processing with Python and spaCy now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.