This chapter will introduce you to NLP, some of its use cases such as named-entity recognition and AI-powered chatbots. You’ll learn how to use the powerful spaCy library to perform various natural language processing tasks such as tokenization, sentence segmentation, POS tagging, and named entity recognition.

Natural Language Processing (NLP) basics

Doc container in spaCy

NER use case

Tokenization with spaCy

spaCy basics

Running a spaCy pipeline

Lemmatization with spaCy

Sentence segmentation with spaCy

Linguistic features in spaCy

POS tagging with spaCy

NER with spaCy

Text processing with spaCy

Introduction to NLP and spaCy

Learn about linguistic features, word vectors, semantic similarity, analogies, and word vector operations. In this chapter you’ll discover how to use spaCy to extract word vectors, categorize texts that are relevant to a given topic and find semantically similar terms to given words from a corpus or from a spaCy model vocabulary.

Linguistic features

Linguistic annotations in spaCy

Word-sense disambiguation with spaCy

Dependency parsing with spaCy

Introduction to word vectors

spaCy vocabulary

Word vectors in spaCy vocabulary

Word vectors and spaCy

Analogies and vector operations

Word vectors projection

Similar words in a vocabulary

Measuring semantic similarity with spaCy

Doc similarity with spaCy

Span similarity with spaCy

Semantic similarity for categorizing text

spaCy Linguistic Annotations and Word Vectors

Get familiar with spaCy pipeline components, how to add a pipeline component, and analyze the NLP pipeline. You will also learn about multiple approaches for rule-based information extraction using EntityRuler, Matcher, and PhraseMatcher classes in spaCy and RegEx Python package.

spaCy pipelines

Adding pipes in spaCy

Analyzing pipelines in spaCy

spaCy EntityRuler

EntityRuler with blank spaCy model

EntityRuler for NER

EntityRuler with multi-patterns in spaCy

RegEx with spaCy

RegEx in Python

RegEx with EntityRuler in spaCy

spaCy Matcher and PhraseMatcher

Matching a single term in spaCy

PhraseMatcher in spaCy

Matching with extended syntax in spaCy

Data Analysis with spaCy

Explore multiple real-world use cases where spaCy models may fail and learn how to train them further to improve model performance. You’ll be introduced to spaCy training steps and understand how to train an existing spaCy model or from scratch, and evaluate the model at the inference time.

Customizing spaCy models

Training spaCy models

Model performance on your data

spaCy training data format

Training steps

Annotation and preparing training data

Compatible training data

Training with spaCy

Training preparation steps

Train an existing NER model

Training a spaCy model from scratch

Wrap-up

Customizing spaCy Models

corona.json

Learn spaCy, the fast-growing industry-standard NLP library, for tasks like tokenization, parsing, and named entity recognition. Master core operations, use classes like Doc and Token, and train models. Extract terms with pattern matching, create custom pipeline components, and handle real-world examples for your NLP projects.


<h2>Meet spaCy, an Industry-Standard for NLP</h2>
In this course, you will learn how to use spaCy, a fast-growing industry-standard library, to perform various natural language processing tasks such as tokenization, sentence segmentation, parsing, and named entity recognition. spaCy can provide powerful, easy-to-use, and production-ready features across a wide range of natural language processing tasks.

<h2>Learn the Core Operations of spaCy</h2>
You will start by learning the core operations of spaCy and how to use them to parse text and extract information from unstructured data. Then, you will work with spaCy’s classes, such as Doc, Span, and Token, and learn how to use different spaCy components for calculating word vectors and predicting semantic similarity.

<h2>Train spaCy Models and Learn About Pattern Matching</h2>
You will practice writing simple and complex matching patterns to extract given terms and phrases using EntityRuler, Matcher, and PhraseMatcher from unstructured data. You will also learn how to create custom pipeline components and create training/evaluation data. From there, you will dive into training spaCy models and how to use them for inference. Throughout the course, you will work on real-world examples and solidify your understanding of using spaCy in your own NLP projects.


Supervised Learning with scikit-learn

Python Toolbox

Master the core operations of spaCy and train models for natural language processing. Extract information from unstructured data and match patterns.

Natural Language Processing with spaCy Course | Master Core Operations and Train Models

Natural Language Processing with spaCy

Scientifique en apprentissage automatique en Python

Traitement du langage naturel en Python

Principal data scientist

Chapter 1 - Introduction to NLP and spaCy

Chapter 2 - spaCy linguistic annotations and word vectors

Chapter 3 - Data analysis with spaCy

Chapter 4 - Customizing spaCy models

Recommended resources

Congratulations!

https://s3.amazonaws.com/assets.datacamp.com/production/course_31481/subtitles/course_31481_707a9ca779a1e266c5f62e0eb3a042f7.vtt

Customizing spaCy Models - Wrap-up

Wrap-up

Create Your Free Account