book

Python Natural Language Processing Cookbook - Second Edition

Name: Python Natural Language Processing Cookbook - Second Edition
ISBN: 9781803245744

by Zhenya Antić, Saurabh Chakravarty

September 2024

Beginner to intermediate

312 pages

7h 18m

English

Packt Publishing

Read now

Unlock full access

Python Natural Language Processing Cookbook
ForewordContributorsAbout the authorsAbout the reviewer
Preface
Who this book is forWhat this book coversTo get the most out of this bookDownload the example code filesConventions usedGet in touchShare Your ThoughtsDownload a free PDF copy of this book
Chapter 1: Learning NLP Basics
Technical requirementsDividing text into sentencesGetting readyHow to do it…There’s more…See alsoDividing sentences into words – tokenizationGetting readyHow to do itThere’s more…There's still moreSee alsoPart of speech taggingGetting readyHow to do it…There’s moreThere’s moreSee alsoCombining similar words – lemmatizationGetting readyHow to do it…There’s more…Removing stopwordsHow to do it…There’s more…There's still more
Chapter 2: Playing with Grammar
Technical requirementsCounting nouns – plural and singular nounsGetting readyHow to do it…There’s more…Getting the dependency parseGetting readyHow to do it…See alsoExtracting noun chunksGetting readyHow to do it…There’s more…See alsoExtracting subjects and objects of the sentenceGetting readyHow to do it…There’s more…Finding patterns in text using grammatical informationGetting readyHow to do it…See also
Chapter 3: Representing Text – Capturing Semantics
Technical requirementsCreating a simple classifierGetting readyHow to do it…There’s more…Putting documents into a bag of wordsGetting readyHow to do it…Constructing an N-gram modelGetting readyHow to do it…There’s more…Representing texts with TF-IDFGetting readyHow to do it…How it works…There’s more…See alsoUsing word embeddingsGetting readyHow to do it…There’s more…See alsoTraining your own embeddings modelGetting readyHow to do it…There’s more…See alsoUsing BERT and OpenAI embeddings instead of  word embeddingsGetting readyHow to do it…There’s more…See alsoRetrieval augmented generation (RAG)Getting readyHow to do it…
Chapter 4: Classifying Texts
Technical requirementsGetting the dataset and evaluation readyGetting readyHow to do it…Performing rule-based text classification using keywordsGetting readyHow to do it…Clustering sentences using K-Means – unsupervised  text classificationGetting readyHow to do it…Using SVMs for supervised text classificationGetting readyHow to do it…There’s more…Training a spaCy model for supervised text classificationGetting readyHow to do it…Classifying texts using OpenAI modelsGetting readyHow to do it…
Chapter 5: Getting Started with Information Extraction
Technical requirementsUsing regular expressionsGetting readyHow to do it…There’s more…Finding similar strings – Levenshtein distanceGetting readyHow to do it…There’s more…Extracting keywordsGetting readyHow to do it…There’s more…Performing named entity recognition using spaCyGetting readyHow to do it…There’s more…Training your own NER model with spaCyGetting readyHow to do it…See alsoFine-tuning BERT for NERGetting readyHow to do it…
Chapter 6: Topic Modeling
Technical requirementsLDA topic modeling with gensimGetting readyHow to do it...There’s more...Community detection clustering with SBERTGetting readyHow to do it...K-Means topic modeling with BERTGetting readyHow to do it...Topic modeling using BERTopicGetting readyHow to do it...There’s more...Using contextualized topic modelsGetting readyHow to do it...See also
Chapter 7: Visualizing Text Data
Technical requirementsVisualizing the dependency parseGetting readyHow to do it...Visualizing parts of speechGetting readyHow to do it...Visualizing NERGetting readyHow to do it...Creating a confusion matrix plotGetting readyHow to do it...Constructing word cloudsGetting readyHow to do it...There’s more...See alsoVisualizing topics from GensimGetting readyHow to do it...See alsoVisualizing topics from BERTopicGetting readyHow to do it...See also
Chapter 8: Transformers and Their Applications
Technical requirementsLoading a datasetGetting readyHow to do it...Tokenizing the text in your datasetGetting readyHow to do it...Classifying textGetting readyHow to do it...Using a zero-shot classifierGetting readyHow to do it...Generating textGetting readyHow to do it...There’s more…Language translationGetting readyHow to do it...

Chapter 9: Natural Language Understanding
Technical requirementsAnswering questions from a short text passageGetting readyHow to do it...Answering questions from a long text passageGetting readyHow to do it...See alsoAnswering questions from a document corpus in an extractive mannerGetting readyHow to do it...See alsoAnswering questions from a document corpus in an abstractive mannerGetting readyHow to do itSee alsoSummarizing text using pre-trained models based on TransformersGetting readyHow to do itThere’s more…See alsoDetecting sentence entailmentGetting readyHow to do it...There’s more...Enhancing explainability via a classifier-invariant approachGetting readyHow to do it...There’s more...Enhancing explainability via text generationGetting readyHow to do it
Chapter 10: Generative AI and Large Language Models
Technical requirementsModel accessRunning an LLM locallyGetting readyHow to do it…Running an LLM to follow instructionsGetting readyHow to do it…There’s more…Augmenting an LLM with external dataExecuting a simple prompt-to-LLM chainAugmenting the LLM with external contentCreating a chatbot using an LLMGetting readyHow to do it…Generating code using an LLMGetting readyHow to do it…There’s more…Generating a SQL query using human-defined requirementsGetting readyHow to do it…Agents – making an LLM to reason and actGetting readyHow to do it…Using OpenAI models instead of local ones
Index
Why subscribe?
Other Books You May EnjoyPackt is searching for authors like youShare Your ThoughtsDownload a free PDF copy of this book

Overview

In Python Natural Language Processing Cookbook, you'll explore over 60 practical recipes designed to enhance your Text Processing and NLP skills. With modern topics like transformer models and Hugging Face libraries, this book provides both foundational learning and cutting-edge techniques used in the industry.

What this Book will help me do

Understand and apply fundamental NLP concepts using Python
Build and customize pipelines for text analysis tasks
Leverage advanced LLMs like GPT-4 for natural language applications
Understand and apply Explainable AI (XAI) in NLP workflows
Visualize and interpret relationships and trends within textual data

Author(s)

Zhenya Antić and Saurabh Chakravarty are experts in computational linguistics and applied NLP. Drawing from years of industry experience, they aim to combine theoretical concepts with practical applications essential for professionals in the field.

Who is it for?

This book is ideal for data scientists and development professionals with a basic programming background interested in gaining fundamental to advanced knowledge of NLP with Python. Whether you aspire to start working on NLP tasks or broaden your expertise with LLMs and XAI, this book is suited for you.

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9781803245744

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills