Natural Language Processing with TensorFlow: Teach language to machines using Python's deep learning library book review

Natural Language Processing is the automatic manipulation of the natural language concerned with the interactions between computers and human languages which provides the majority of data available to deep learning applications. Tensorflow is is the most important deep learning framework currently available.
Following are the number of NLP tasks that can be accomplished using TensorFlow APIs:
- Word embedding
- Language modeling
- Part-of-speech tagging
- Name entity detection
- Parsing
- Translation.
Here is the book of Natural Language Processing with TensorFlow: Teach language to machines using Python's deep learning library
About the author
The writer of this book, Thushan Ganegedara is currently a third-year Ph.D. student at the University of Sydney, Australia. He is specializing in machine learning and runs algorithms on untested data. He has a liking for deep learning and works as the chief data scientist for AssessThreat, an Australian start-up. He got his BSc. (Hons) from the University of Moratuwa, Sri Lanka. He also frequently writes technical articles and tutorials about machine learning.
About the book
Natural Language Processing with TensorFlow is a great book if you want to learn the practical application of NLP on Tensorflow. Natural language processing (NLP) provides the majority of data available to deep learning applications, while TensorFlow is the most important deep learning framework currently available. In this book, Thushan discusses the basics of TensorFlow and illustrates the workflow with a colorful example. The book touches upon a multitude of NLP applications, providing a very diverse practical exposure to the current NLP solutions and focuses on more efficient natural language processing using TensorFlow.
What you will learn from this book
- Apply the tools to specific NLP tasks
- How to use Word2vec, including advanced extensions
- How to create word embeddings that turn sequences of words into vectors accessible to deep learning algorithms
- Apply high-performance RNN models, like long short-term memory (LSTM) cells, to NLP tasks
- You will explore and implement a neural machine translator
- Apply TensorFlow in deep learning NLP applications, and how to perform specific NLP tasks
- Strategies to process large amounts of data into word representations that can be used by deep learning applications
- How to write automatic translation programs and implement an actual neural machine translator from scratch
- The trends and innovations that are paving the future in NLP
Key contents are
- Introduction
- How to get TensorFlow to work
- Producing word embeddings with word2Vec
- Advanced word2Vec
- Sentence classification with CNN's
- Language modeling with RNNs
- What is LSTM?
- Applying LSTM to text generation
- Applications of LSTM: image caption generation
- Neural machine translation
- NLP developments and trends
- Appendix I linear algebra and statistics
This book is highly recommended for
- Python developers with a strong interest in deep learning,
- People who want to learn how to leverage TensorFlow to simplify NLP tasks.
- Those who have some knowledge of machine learning
- Undergraduate-level calculus and linear algebra.
Discussion
If you read this book you will gain an understanding of NLP and TensorFlow basics. You will be able to Write modern natural language processing applications using deep learning algorithms and TensorFlow. It is a great book on convolutional neural networks (CNN) and recurrent neural networks (RNN) etc. After reading this book you will be able to do many things including how to apply the TensorFlow toolbox to specific tasks in the most interesting field in artificial intelligence. This book covers NLP as a field in its own right to improve understanding for choosing TensorFlow tools and other deep learning approaches.
Also you can check best books to build machine learning models with TensorFlow