This chapter will introduce you to the basics of text processing with spaCy. You'll learn about the data structures, how to work with statistical models, and how to use them to predict linguistic features in your text.

Introduction to spaCy

Getting Started

Documents, spans and tokens

Lexical attributes

Statistical models

Model packages

Loading models

Predicting linguistic annotations

Predicting named entities in context

Rule-based matching

Using the Matcher

Writing match patterns

Finding words, phrases, names and concepts

In this chapter, you'll use your new skills to extract specific information from large volumes of text. You'll learn how to make the most of spaCy's data structures, and how to effectively combine statistical and rule-based approaches for text analysis.

Data Structures (1)

Strings to hashes

Vocab, hashes and lexemes

Data Structures (2)

Creating a Doc

Docs, spans and entities from scratch

Data structures best practices

Word vectors and similarity

Inspecting word vectors

Comparing similarities

Combining models and rules

Debugging patterns (1)

Debugging patterns (2)

Efficient phrase matching

Extracting countries and relationships

Large-scale data analysis with spaCy

This chapter will show you to everything you need to know about spaCy's processing pipeline. You'll learn what goes on under the hood when you process a text, how to write your own components and add them to the pipeline, and how to use custom attributes to add your own meta data to the documents, spans and tokens.

Processing pipelines

What happens when you call nlp?

Inspecting the pipeline

Custom pipeline components

Use cases for custom components

Simple components

Complex components

Extension attributes

Setting extension attributes (1)

Setting extension attributes (2)

Entities and extensions

Components with extensions

Scaling and performance

Processing streams

Processing data with context

Selective processing

Processing Pipelines

In this chapter, you'll learn how to update spaCy's statistical models to customize them for your use case – for example, to predict a new entity type in online comments. You'll write your own training loop from scratch, and understand the basics of how training works, along with tips and tricks that can make your custom NLP projects more successful.

Addestrare e aggiornare i modelli

Scopo dell'addestramento

Creare dati di training (1)

Creare dati di training (2)

Il ciclo di training

Configurare la pipeline

Creare un training loop

Esplorare il modello

Best practice per l'addestramento

Dati buoni vs. dati scarsi

Addestrare più etichette

Ricapitolo

Training a neural network model

Se lavori con molti testi, prima o poi vorrai saperne di più. Ad esempio: di cosa parlano? Cosa significano le parole nel contesto? Chi fa cosa a chi? Quali aziende e prodotti sono menzionati? Quali testi sono simili tra loro? In questo corso imparerai a usare spaCy, una libreria per NLP in Python sempre più diffusa nel settore, per creare sistemi avanzati di comprensione del linguaggio naturale, utilizzando sia approcci basati su regole sia di Machine Learning.

Introduction to Natural Language Processing in Python

Impara a usare spaCy per creare sistemi avanzati di comprensione del linguaggio naturale.

NLP avanzato con spaCy

Configurare la pipeline

NLP avanzato con spaCy

Esercizio pratico interattivo