Mastering spaCy

Duygu Altinok

• Publisher: Packt Publishing
• Year: 2021
• ISBN:
  9781800561120
• Edition: 1
• Topic: Computer Science
• Subtopic: Data Processing
• Index: Computer Science

Build end-to-end industrial-strength NLP models using advanced morphological and syntactic features in spaCy to create real-world applications with easeKey Features• Gain an overview of what spaCy offers for natural language processing• Learn details of spaCy's features and how to use them effectively• Work through practical recipes using spaCyBook DescriptionspaCy is an industrial-grade, efficient NLP Python library. It offers various pre-trained models and ready-to-use features. Mastering spaCy provides you with end-to-end coverage of spaCy's features and real-world applications.You'll begin by installing spaCy and downloading models, before progressing to spaCy's features and prototyping real-world NLP apps. Next, you'll get familiar with visualizing with spaCy's popular visualizer displaCy. The book also equips you with practical illustrations for pattern matching and helps you advance into the world of semantics with word vectors. Statistical information extraction methods are also explained in detail. Later, you'll cover an interactive business case study that shows you how to combine all spaCy features for creating a real-world NLP pipeline. You'll implement ML models such as sentiment analysis, intent recognition, and context resolution. The book further focuses on classification with popular frameworks such as TensorFlow's Keras API together with spaCy. You'll cover popular topics, including intent classification and sentiment analysis, and use them on popular datasets and interpret the classification results.By the end of this book, you'll be able to confidently use spaCy, including its linguistic features, word vectors, and classifiers, to create your own NLP apps.What you will learn• Install spaCy, get started easily, and write your first Python script• Understand core linguistic operations of spaCy• Discover how to combine rule-based components with spaCy statistical models• Become well-versed with named entity and keyword extraction• Build your own ML pipelines using spaCy• Apply all the knowledge you've gained to design a chatbot using spaCyWho this book is forThis book is for data scientists and machine learners who want to excel in NLP as well as NLP developers who want to master spaCy and build applications with it. Language and speech professionals who want to get hands-on with Python and spaCy and software developers who want to quickly prototype applications with spaCy will also find this book helpful. Beginner-level knowledge of the Python programming language is required to get the most out of this book. A beginner-level understanding of linguistics such as parsing, POS tags, and semantic similarity will also be useful.

Section 1: Getting Started with spaCy

This section will begin with an overview of natural language processing (NLP) with Python and spaCy. You will learn how the book is organized and how to make the best use of the book. You will then start by installing spaCy and its statistical models and take a quick dive into the spaCy world. Basic operations, general conventions, and visualization are the core attractions of this section.

This section comprises the following chapters:

• Chapter 1, Getting Started with spaCy
• Chapter 2, Core Operations with spaCy

Chapter 1: Getting Started with spaCy

In this chapter, we will have a comprehensive introduction to natural language processing (NLP) application development with Python and spaCy. First, we will see how NLP development goes hand in hand with Python, along with an overview of what spaCy offers as a Python library.

After the warm-up, you will quickly get started with spaCy by downloading the library and loading the models. You will then explore spaCy's popular visualizer displaCy by visualizing several features of spaCy.

By the end of this chapter, you will know what you can achieve with spaCy and how to plan your journey with spaCy code. You will be also settled with your development environment, having already installed all the necessary packages for NLP tasks in the upcoming sections.

We're going to cover the following main topics in this chapter:

• Overview of spaCy
• Installing spaCy
• Installing spaCy's statistical models
• Visualization with displaCy

Technical requirements

The chapter code can be found at the book's GitHub repository: https://github.com/PacktPublishing/Mastering-spaCy/tree/main/Chapter01

Overview of spaCy

Before getting started with the spaCy code, we will first have an overview of NLP applications in real life, NLP with Python, and NLP with spaCy. In this section, we'll find out the reasons to use Python and spaCy for developing NLP applications. We will first see how Python goes hand-in-hand with text processing, then we'll understand spaCy's place in the Python NLP libraries. Let's start our tour with the close-knit relationship between Python and NLP.

Rise of NLP

Over the past few years, most of the branches of AI created a lot of buzz, including NLP, computer vision, and predictive analytics, among others. But just what is NLP? How can a machine or code solve human language?

NLP is a subfield of AI that analyzes text, speech, and other forms of human-generated language data. Human language is complicated – even a short paragraph contains references to the previous words, pointers to real-world objects, cultural references, and the writer's or speaker's personal experiences. Figure 1.1 shows such an example sentence, which includes a reference to a relative date (recently), phrases that can be resolved only by another person who knows the speaker (regarding the city that the speaker's parents live in) and who has general knowledge about the world (a city is a place where human beings live together):

Figure 1.1 – An example of human language, containing many cognitive and cultural aspects

How do we process such a complicated structure then? We have our weapons too; we model natural language with statistical models, and we process linguistic features to turn the text into a well-structured representation. This book provides all the necessary background and tools for you to extract the meaning out of text. By the end of this book, you will possess statistical and linguistic knowledge to process text by using a great tool – the spaCy library.

Though NLP gained popularity recently, processing human language has been present in our lives via many real-world applications, including search engines, translation services, and recommendation engines.

Search engines such as Google Search, Yahoo Search, and Microsoft Bing are an integral part of our daily lives. We look for homework help, cooking recipes, information about celebrities, the latest episodes of our favorite TV series; all sorts of information that we use in our daily lives. There is even a verb in English (also in many other languages), to google, meaning to look up some information on the Google search engine.

Search engines use advanced NLP techniques including mapping queries into a semantic space, where similar queries are represented by similar vectors. A quick trick is called autocomplete, where query suggestions appear on the search bar when we type the first few letters. Autocomplete looks tricky but indeed the algorithm is a combination of a search tree walk and character-level distance calculation. A past query is represented by a sequence of its characters, where each character corresponds to a node in the search tree. The arcs between the characters are assigned weights according to the popularity of this past query.

Then, when a new query comes, we compare the current query string to past queries by walking on the tree. A fundament...