Chapter 7: Customizing spaCy Models
In this chapter, you will learn how to train, store, and use custom statistical pipeline components. First, we will discuss when exactly we should perform custom model training. Then, you will learn a fundamental step of model training – how to collect and label your own data.
In this chapter, you will also learn how to make the best use of Prodigy, the annotation tool. Next, you will learn how to update an existing statistical pipeline component with your own data. We will update the spaCy pipeline's named entity recognizer (NER) component with our own labeled data.
Finally, you will learn how to create a statistical pipeline component from scratch with your own data and labels. For this purpose, we will again train an NER model. This chapter takes you through a complete machine learning practice, including collecting data, annotating data, and training a model for information extraction.
By the end of this chapter, you&apos...
