Practical Natural Language Processing

The best Natural Language Processing book for everyone

The following is a review of the book Practical Natural Language Processing: A Comprehensive Guide to Building Real-World NLP Systemsby Sawmya Vajjala, Bodhisattwa Majumder, Anuj Gupta & Harshit Surana, a Natural Language Processing book suited for all audiences.

Review of Practical Natural Language Processing

Natural Language Processing, sometimes also called Text Mining, is one of the most promising areas of Machine Learning. With some much text data being generated and flying around, the value institutions, businesses, and research can extract from it is unlimited.

However, despite it having so much potential, there are not many experts at it, and companies tend to struggle to exploit their various forms of unstructured text data like emails, news, or social media feeds.

Many books and courses tackle natural language processing (NLP) problems with toy use cases and well-defined, easy, and in the end unrealistic datasets, that don’t reflect what data looks like in the real world.

If you want to build, iterate, and scale Natural Language Processing systems in a business setting and tailor them for particular industry verticals, you need a realistic text analysis or text mining book: this is your guide.

Software engineers and data scientists will learn how to navigate the maze of options available at each step of text processing journey, product managers and higher level executives will understand how NLP can be used to benefit their business, and startup owners will learn how to benefit from using this wonderful technology, just by reading this great document: for us it is one of the best text mining books out there, as it serves a wide variety of readers.

Through the course of Practical Natural Language Processing: A Comprehensive Guide to Building Real-World NLP Systems, authors Sowmya Vajjala, Bodhisattwa Majumder, Anuj Gupta, and Harshit Surana will guide you through the process of building real-world NLP solutions embedded in larger product setups. You’ll learn how to adapt your solutions for different industry verticals such as healthcare, social media, and retail.

With this book, you’ll:

• Understand the wide spectrum of problem statements, tasks, and solution approaches within NLP.
• Implement and evaluate different NLP applications using machine learning and deep learning methods.
• Fine-tune your NLP solution based on your business problem and industry vertical.
• Evaluate various algorithms and approaches for NLP product tasks, datasets, and stages.
• Produce software solutions following best practices around release, deployment, and DevOps for NLP systems.
• Understand best practices, opportunities, and the roadmap for NLP from a business and product leader’s perspective.

You can find the official Github Repository of the book here.

Practical Natural Language Processing is not a deeply technical book that covers this field like Dan jurafsky NLP book: while it does provide some technical insight and covers things like Neural Network architectures and best practices, it also provides comprehensive explanations of how NLP can impact different industrial sectors from a high level point of view, which will prove to be useful for both, deeply technical readers, and those with less technical expertise looking to understand what this technology can do for them.

Because of this mix and compromise, we consider it one of the best natural language processing books to get started with, that provides an introduction on how to apply NLP in the industrial setting and a comprehensive big picture for the current main breakthroughs in this field, combining the real-life case studies as well code.

Who is this book for:

Practical Natural Language Processing, as we mentioned before, is a Natural Language Processing book that is suitable for a wide spectrum of readers:

• A software engineer or a data scientist who needs to build real-world NLP systems
• A machine learning engineer who has to iterate and scale NLP systems
• A product manager who needs to understand NLP and how it can be applied to their domain
• A business leader who wants to start a new venture based on NLP or incorporate the cutting edge of NLP in existing products

Contents of Practical Natural Language Processing

The contents of this NLP book are the following:

1. NLP: A primer – How Natural Language Processing is used in the real world, how it is derived from Machine Learning, the difficulties of NLP, and some approaches to it.
2. NLP Pipeline: From text acquisition to clean up, parsing and spelling correction, pre-processing techniques and necessities, and modelling and evaluation.
3. Text Representation: One hot encoding, Bag of Words, N grams, TF-IDF, and the widely used word embeddings.
4. Text Classification: Different text classification techniques used for tasks like spam or ham, and the most known APIs. Techniques like Naive Bayes Classifier, Logistic Regression or Support Vector Machines. Also, the most common architectures for Text Classificaiton (CNNs and LSTM, by the way, we have a great article about LSTMs in NLP that you can find here) and how to use pre-trained models and explain their output using libraries like Lime.
5. Information Extraction: The general pipeline of IFE, Keyphrase extraction, Named Entity Recognition (NER), Named Entity Disambiguation, Relationship extraction and other similar tasks.
6. Chatbots: Who doesn’t love a good chatbot? This chapter is dedicated to how to create one. Check out this Medium post by one of our friends if you are curious about them.

7. Topics in Brief: this is a great natural language processing book, that does not leave anything outside. This chapter covers how to build a search engine like our famous Google, topics like Text Summarization (using large corpus of texts to build a headline, for news articles for example), or Recommender Systems and Machine Translation.

8. Social Media: Applications of Natural Language Processing for Social Media, and extracting value from Data derived from platforms like Twitter. Awesome articles about this here and here.

9. E-commerce and Retail: How e-commerce benefits from the large amount of unstructured text data floating around, and how to leverage it with NLP with techniques like Sentiment Analysis.

10. Healthcare, Finance, and Law: Again, how other industries can benefit from the advances in Natural Language Processing. As we mentioned this Natural Language Processing book leaves no stone unturned.

11. The end to end NLP Process: A whole NLP Pipeline, how to build and maintain a system, and how to make AI Succeed at your organisation – Building a team, defining the problem, objectives, and relevant data.

As you can see the book is very through and it covers a lot of topics. This is one of the reasons we love it, as it hits the sweet-spot between a tech and a business book and it is still very easy to read.

Summary

Practical Natural Language Processing: A Comprehensive Guide to Building Real-World NLP Systems provides a high overview of Natural Language processing that can suit both people with technical experience in the Data Science field, and those with no programming or tech background that want to understand how leveraging text data and data science can evolve their organisations and businesses to the next level.

As we saw in the contents, the book includes how NLP can affect various industries, like E-commerce, Healthcare, and Law, which is not something that is covered in more deeply technical texts. Still, there are plenty of references in the book that will guide you to more technical caves if you are looking for that.

We recommend this book to beginners in the field of Natural Language Processing and professionals who want to see how NLP can impact their business: everybody will gain something after reading regardless of the experience level. It is definitely worth the money and the time. You can find it this great text analysis book on Amazon at the best price here:

Practical Natural Language Processing: The Natural Language Processing book for everybody

If you think this book wasn’t too advanced for you, don’t worry we’ve got you covered. Check out our reviewed list of Machine Learning Courses. Also you can find a great list of free reviewed Statistics and Probability Courses here.

For more technical Machine Learning resources, after one of these courses, we would recommend a book like ‘The Elements of Statistical Learning‘ or even simpler ‘The Hundred Page Machine Learning book‘. The previous links will take you to reviews about these two where you can decide if the books are the right for you: They are quite theoretical, but very interesting.

If these still don’t convince you, take a stroll through our Machine Learning books section, or to find texts about probability check out our Data Analysis books sections.

Also, here you can find great free tutorials about these topics.

Also, if you have any suggestions about any other Natural Language Processing books, please give us a poke at howtolearnmachinelearning@gmail.com or just comment on this post!

That is all, we hope you loved the review. If you want to keep up to date with the newest materials and resources to learn Machine Learning, follow us on Twitter!