spaCy        
                                                     i 
                           
                                                  spaCy        
        About the Tutorial 
        spaCy, developed by software developers Matthew Honnibal and Ines Montani, is an 
        open-source software library for advanced NLP (Natural Language Processing). It is written 
        in Python and Cython (C extension of Python which is mainly designed to give C like 
        performance to the Python language programs). spaCy is a relatively new framework but 
        one of the most powerful and advanced libraries used to implement NLP.      
        Audience 
        This tutorial will be useful for graduates, post-graduates, and research students who either 
        have an interest in NLP or have these subjects as a part of their curriculum. The reader 
        can be a beginner or an advanced learner.  
        Prerequisites 
        The reader must have basic knowledge about NLP and artificial intelligence. He/she should 
        also  be  aware  about  the  basic  terminologies  used  in  English  grammar  and  Python 
        programming concepts. 
        Copyright & Disclaimer 
         Copyright 2021 by Tutorials Point (I) Pvt. Ltd.  
        All the content and graphics published in this e-book are the property of Tutorials Point (I) 
        Pvt. Ltd.  The user of this e-book is prohibited to reuse, retain, copy, distribute or republish 
        any contents or a part of contents of this e-book in any manner without written consent 
        of the publisher.   
        We strive to update the contents of our website and tutorials as timely and as precisely as 
        possible, however, the contents may contain inaccuracies or errors. Tutorials Point (I) Pvt. 
        Ltd. provides no guarantee regarding the accuracy, timeliness or completeness of our 
        website or its contents including this tutorial. If you discover any errors on our website or 
        in this tutorial, please notify us at contact@tutorialspoint.com 
         
         
         
         
         
         
                       
                                                     i 
                           
                                                                                                                                                  spaCy        
                      Table of Contents 
                           About the Tutorial ............................................................................................................................................ i 
                           Audience ........................................................................................................................................................... i 
                           Prerequisites ..................................................................................................................................................... i 
                           Copyright & Disclaimer ..................................................................................................................................... i 
                           Table of Contents ............................................................................................................................................ ii 
                      1.   spaCy — Introduction ............................................................................................................................... 1 
                           Extensions and visualisers ............................................................................................................................... 1 
                      2.   spaCy — Getting Started ........................................................................................................................... 4 
                      3.   spaCy — Models and Languages ............................................................................................................... 9 
                      4.   spaCy — Architecture ............................................................................................................................. 15 
                      5.   spaCy — Command Line Helpers ............................................................................................................. 18 
                      6.   spaCy — Top-level Functions .................................................................................................................. 32 
                      7.   spaCy — Visualization Function .............................................................................................................. 36 
                      8.   spaCy — Utility Functions ....................................................................................................................... 44 
                      9.   spaCy — Compatibility Functions ............................................................................................................ 59 
                      10.  spaCy — Containers ................................................................................................................................ 61 
                      11.  spaCy — Doc Class ContextManager and Property .................................................................................. 70 
                           Retokenizer.split ............................................................................................................................................ 72 
                      12.  spaCy — Container Token Class .............................................................................................................. 78 
                      13.  spaCy — Token Properties ...................................................................................................................... 89 
                      14.  spaCy — Container Span Class ................................................................................................................ 95 
                      15.  spaCy — Span Class Properties ............................................................................................................. 103 
                      16.  spaCy — Container Lexeme Class .......................................................................................................... 110 
                      17.  spaCy — Training Neural Network Model ............................................................................................. 117 
                           Steps for Training ........................................................................................................................................ 117 
                      18.  spaCy — Updating Neural Network Model ........................................................................................... 120 
                                                                                                                                                          ii 
                                                                             
                                          1.  spaCy — Introduction                                                                      spaCy        
                    In this chapter, we will understand the features, extensions and visualisers with regards 
                    to spaCy. Also, a features comparison is provided which will help the readers in analysis 
                    of the functionalities provided by spaCy as compared to Natural Language Toolkit (NLTK) 
                    and coreNLP. Here, NLP refers to Natural Language Processing. 
                    What is spaCy? 
                    spaCy, which is developed by the software developers Matthew Honnibal and Ines 
                    Montani, is an open-source software library for advanced NLP. It is written in Python and 
                    Cython (C extension of Python which is mainly designed to give C like performance to the 
                    Python language programs).  
                    spaCy is a relatively a new framework but, one of the most powerful and advanced libraries 
                    which is used to implement the NLP.    
                    Features 
                    Some of the features of spaCy that make it popular are explained below: 
                    Fast: spaCy is specially designed to be as fast as possible. 
                     
                    Accuracy:  spaCy implementation of its labelled dependency parser makes it one of the 
                    most accurate frameworks (within 1% of the best available) of its kind. 
                     
                    Batteries included: The batteries included in spaCy are as follows: 
                             Index preserving tokenization. 
                             “Alpha tokenization” support more than 50 languages. 
                             Part-of-speech tagging. 
                             Pre-trained word vectors. 
                             Built-in easy and beautiful visualizers for named entities and syntax. 
                             Text classification. 
                                         
                    Extensile: You can easily use spaCy with other existing tools like TensorFlow, Gensim, 
                    scikit-Learn, etc. 
                     
                    Deep learning integration: It has Thinc-a deep learning framework, which is designed 
                    for NLP tasks. 
                    Extensions and visualisers 
                    Some of the easy-to-use extensions and visualisers that comes with spaCy and are free, 
                    open-source libraries are listed below: 
                    Thinc: It is Machine Learning (ML) library optimised for Central Processing Unit (CPU) 
                    usage. It is also designed for deep learning with text input and NLP tasks. 
                                                                                                                                              1