This textbook explains Deep Learning Architecture, with applications to various NLP Tasks, including Document Classification, Machine Translation, Language Modeling, and Speech Recognition. With the widespread adoption of deep learning, natural language processing (NLP),and speech applications in many areas (including Finance, Healthcare, and Government) there is a growing need for one comprehensive resource that maps deep learning techniques to NLP and speech and provides insights into using the tools and libraries for real-world applications. Deep Learning for NLP and Speech Recognition explains recent deep learning methods applicable to NLP and speech, provides state-of-the-art approaches, and offers real-world case studies with code to provide hands-on experience.
Many books focus on deep learning theory or deep learning for NLP-specific tasks while others are cookbooks for tools and libraries, but the constant flux of new algorithms, tools, frameworks, and libraries in a rapidly evolving landscape means that there are few available texts that offer the material in this book.
The book is organized into three parts, aligning to different groups of readers and their expertise. The three parts are:
Machine Learning, NLP, and Speech Introduction
The first part has three chapters that introduce readers to the fields of NLP, speech recognition, deep learning and machine learning with basic theory and hands-on case studies using Python-based tools and libraries.
Deep Learning Basics
The five chapters in the second part introduce deep learning and various topics that are crucial for speech and text processing, including word embeddings, convolutional neural networks, recurrent neural networks and speech recognition basics. Theory, practical tips, state-of-the-art methods, experimentations and analysis in using the methods discussed in theory on real-world tasks.
Advanced Deep Learning Techniques for Text and Speech
The third part has five chapters that discuss the latest and cutting-edge research in the areas of deep learning that intersect with NLP and speech. Topics including attention mechanisms, memory augmented networks, transfer learning, multi-task learning, domain adaptation, reinforcement learning, and end-to-end deep learning for speech recognition are covered using case studies.
Sale!
Deep Learning for NLP and Speech Recognition
Original price was: $ 29,99.$ 19,99Current price is: $ 19,99.
🔒 Safe & Secure Checkout
bookbug –
A great resource for having the concept, theory and the use cases all in one place. Not only basic NLP concepts such as word embeddings, convolutional neural networks, and recurrent networks are well explained with NLP domain, but the case study covers many standard and advanced methods in each using Keras or PyTorch very well. There are very few books or resources that cover the advanced chapters such as the Attention & Memory Networks, Domain Adaptation, and Reinforcement learning in a comprehensive way with the case studies, so definitely a big plus! Highly recommend.
Charlie A –
Let me be very clear. I am not interested in leaving reviews unless I am firmly compelled to do so. This summer I was interested in NLP and knowing John Liu in the Nashville data science community, I thought I would give it a read. Now, as many of these books go, it is a comprehensive books that is not best read cover to cover. But instead, start with the beginning and then find the sections that are best suited for you.
This is a book that may be a little tough for the beginner, but it is very well written that even the novice will understand their chapters on machine learning and the basics of deep learning. I was very interested in learning more about recurrent and concurrent neural networks and this book did not disappoint. I do have some mathematics background, but even without this knowledge, I feel that I would have still understood the book.
Well done and thank you writing a book on this subject that will be interesting for a wide range of individuals. Its practical basis made it easy to follow and (believe it or not) a joy to read. This will be my reference for NLP and speech recognition.
Raj Pai –
I have done ML many years ago. This book really helped me brush up on my fundmanetals around how ML and deep learning work and then went deeper into the latest state of the art for NLP and Speech Recognition explains recent deep learning methods applicable to NLP and speech with real-world case studies and relevant code and access for were to find libraries for a hands-on experience.
Loved the book and is helping me enormously in driving my teams to rethink through some of the work we are doing…
Nishikant D. –
I got an early copy of this highly rated author Dr. Uday Kamath of “Mastering Java Machine Learning.” Having a good understanding of machine learning but not ventured into Deep Learning and NLP/Speech, this book gave me a good overview starting from basics and most importantly the case studies with a hands-on approach to algorithms, comparisons, validation, etc. is helpful for a practitioner like me.
Lindsey C. –
“Deep Learning for NLP and Speech Recognition” is a comprehensive text that walks the reader through a complex topic in a thoughtful and easily consumable way. Chapter 3 on “Text and Speech Basics” sets the stage for contextual understanding of natural language processing, critical for the ability to apply algorithms effectively to speech data. The authors weave Python snippets of analysis and case studies throughout the text, making application of the methodologies easy for the learner. Over 13 chapters, the concepts build upon each other, and the reader walks away with a comprehensive study of NLP and several deep learning methodologies, which can be applied to non-NLP problems. I especially enjoyed section 7.6, as the authors deftly describe how to convert language data and word embeddings into inputs for a recurrent neural network. Extensive and thorough resource for both scientists with proficient knowledge of NLP and scientists just getting started.
Rabiraj Banerjee –
This book is great, because the authors have supported theory with code Snippets of PyTorch which really helps in understanding, but I found a bit of a problem in the BPTT Derivation, there they have not used the summation symbol while calculating the loss which is usually a scalar, I had to derive the whole BPTT on my own after some intense reading from a Stanford presentation to confirm whether I was right or wrong. Other than that this book is just great 🙂
Sunil Bharitkar –
Very nicely written book!
Oh, bichinho! –
THE BEST BOOK UPDATED (2019) FOR NLP/SPEECH RECOGNITION AND DEEP LEARNING;
FOR ANYONE INTERESTED IN THE FIELD OF DEEP LEARNING AND NLP, I STRONGLY RECOMMEND THIS BOOK;
Dale –
I do like that the book is up-to-date, extensive and related to github projects in the form of dockers. This way it literally take an hour to learn about a new concept and then run the code to train the model and try out tuning parameters. A good summary like this is much needed and comes handy.
A. Boros –
This book is encyclopedic summary of all NLP deep learning and also contains a short but great summary of deep reinforcement learning.
inlori Customer –
I am only 70 pages in, but I find this book to be very sloppily written. Numerous mistakes/typos in the math equations. So far I felt the book can only serve as quick reminders of what you already know, but it tends to gloss over things so don’t expect to get too many technical details from it. Hope it gets better in future chapters.
Massimo B. –
Very well written
Jack Carmody –
Wish I had it on the ipad as well as in hard copy
antonio dantas –
Good on deep learning math. It covers neural networks fundamentals and presents interesting nlp use cases, with tools and datasets.