Natural Language Processing with TensorFlow: The definitive NLP book to implement the most sought-after machine learning models and tasks, 2nd Edition

"Having worked on Natural Language Processing (NLP) for several decades, I can certify that this book will not only get you started in NLP, but take you to the state of art models such as Transformers for NLP and image captioning. The author does a great job with the open source programs using a wide range of frameworks including Hugging Face. This book will take you on an exciting journey into NLP."

-- Denis Rothman, Author of the bestselling book Transformers for Natural Language Processing

"This book addresses the important need of describing how Natural Language Processing (NLP) problems can be solved using TensorFlow-based NLP stacks. This book provides detailed knowledge of NLP methods, from their definition to various evaluation methods. There is information about TensorFlow, Keras, and Hugging Face libraries, which are powerful tools to build such NLP solutions. You'll learn about neural architectures, which is important for building better models by building architectures for specific tasks you will meet in practice."

-- Andrei Lopatenko, VP Engineering, Head of Search & NLP, Zillow

"This book will be useful for a range of different NLP practitioners as it covers both foundational topics, such as word embeddings, and more advanced deep learning techniques, such as RNNs and Transformers. Every technique is applied to a real problem, which is a great way to show the potential uses of the technology. All the content is well explained using the latest version of TensorFlow, which makes this an ideal choice for those looking to learn how to use the framework. The writing is clear and easy to follow, and the book provides ample background for each new topic. This is a must-have for any NLP enthusiast!"

-- Rafael Pssas, Applied Scientist, Amazon

"The book is well organized and easy to follow. For beginners, it is very useful because it follows a logical and coherent order for NLP: TF basics -> distributed representations -> simple models -> complex models. The code is mostly self-contained and easy to follow, and the diagrams + visualizations will help beginners understand core NLP concepts. For more advanced users looking to switch from PyTorch or other tools, it is easy to skip to more advanced chapters to look at implementation patterns for common tasks (embeddings, residuals, tokenizing, preprocessing, multi-modal usage, among others)."

Revanth Rameshkumar, Machine Learning Engineer, Stripe

Thushan is a seasoned ML practitioner with 4+ years of experience in the industry. Currently he is a senior machine learning engineer at Canva; an Australian startup that founded the online visual design software, Canva, serving millions of customers. His efforts are particularly concentrated in the search and recommendations group working on both visual and textual content. Prior to Canva, Thushan was a senior data scientist at QBE Insurance; an Australian Insurance company. Thushan was developing ML solutions for use-cases related to insurance claims. He also led efforts in developing a Speech2Text pipeline there. He obtained his PhD specializing in machine learning from the University of Sydney in 2018.