Develop your NLP skills from scratch, with an open source toolbox of Python packages, Transformers, Hugging Face, vector databases, and your own Large Language Models.
Natural Language Processing in Action, Second Edition has helped thousands of data scientists build machines that understand human language. In this new and revised edition, you’ll discover state-of-the art Natural Language Processing (NLP) models like BERT and HuggingFace transformers, popular open-source frameworks for chatbots, and more. You’ll create NLP tools that can detect fake news, filter spam, deliver exceptional search results and even build truthfulness and reasoning into Large Language Models (LLMs).
In Natural Language Processing in Action, Second Edition you will learn how to:
Process, analyze, understand, and generate natural language text
Build production-quality NLP pipelines with spaCy
Build neural networks for NLP using Pytorch
BERT and GPT transformers for English composition, writing code, and even organizing your thoughts
Create chatbots and other conversational AI agents
In this new and revised edition, you’ll discover state-of-the art NLP models like BERT and HuggingFace transformers, popular open-source frameworks for chatbots, and more. Plus, you’ll discover vital skills and techniques for optimizing LLMs including conversational design, and automating the “trial and error” of LLM interactions for effective and accurate results.
About the Technology From nearly human chatbots to ultra-personalized business reports to AI-generated email, news stories, and novels, natural language processing (NLP) has never been more powerful! Groundbreaking advances in deep learning have made high-quality open source models and powerful NLP tools like spaCy and PyTorch widely available and ready for production applications. This book is your entrance ticket—and backstage pass—into the next generation of natural language processing.
About the Book Natural Language Processing in Action, Second Edition introduces the foundational technologies and state-of-the-art tools you’ll need to write and publish NLP applications. You learn how to create custom models for search, translation, writing assistants, and more, without relying on big commercial foundation models. This fully updated second edition includes coverage of BERT, Hugging Face transformers, fine-tuning large language models, and more.
What's Inside
NLP pipelines with spaCy
Neural networks with PyTorch
BERT and GPT transformers
Conversational design for chatbots
About the Reader For intermediate Python programmers familiar with deep learning basics.
About the Authors Hobson Lane is a data scientist and machine learning engineer with over twenty years of experience building autonomous systems and NLP pipelines. Maria Dyshel is a social entrepreneur and artificial intelligence expert, and the CEO and cofounder of Tangible AI.
Cole Howard and Hannes Max Hapke were co-authors of the first edition.
Quotes Comprehensive. This book tells you how NLP works under the covers. - Andrew R Freed, IBM
A must-read! It turns complex concepts into an engaging journey. - Chunxu Tang, Alluxio
The Bible for anyone interested in NLP and LLMs. - Julien Pohie, Thoughtworks
Essential reading for any startup founder. - Santosh Balajee Banisetty, Zebu Intelligent Systems
A fantastic book packed with great examples. - Sören Schellhoff, IITS Consulting
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.
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.