How Practical NLP was born

The authors have been building and scaling NLP solutions for over a decade at leading universities and technology companies. While mentoring colleagues and other engineers, they noticed a gap between NLP practice in the industry and the NLP skill set of new engineers or those who are experienced but just starting with NLP in particular. Authors started understanding these gaps even better with NLP workshops they were conducting for industry professionals where they noticed that business and engineering leaders also suffer from these gaps.

Most of the online courses and books tackle NLP problems using toy use cases and popular (often large, clean and well defined) datasets. While this teaches the readers general methods, authors have seen that it does not give enough foundation to tackle new problems and develop complete solutions in the real world. Commonly encountered problems while building real world applications such as data collection, working with noisy data and signals, incremental development of solutions, and issues involved in deploying the solutions as a part of a larger application are generally not dealt with by existing resources on the topic. They also saw best practices to develop NLP systems were missing in most scenarios and this book was needed to bridge this gap.

What the book covers

This book gives a comprehensive view on building real world NLP applications. it covers the complete lifecycle of a typical NLP project - right from data collection to deploying and monitoring the model. Some of these steps are applicable to any ML pipeline while some are very specific to NLP. The book also introduces task-specific case studies and domain-specific guides to build an NLP system from scratch. Specifically it covers a gamut tasks ranging from text classification to question answering, information extraction to dialog systems. Similarly, it provides recipes to apply these tasks in domains ranging from e-commerce to healthcare, social media to law. The book also covers case studies and best practices from the viewpoint of business, engineering and product leaders to help them run NLP projects smoothly.

Owing to the depth and breadth of the topics and scenarios that are covered, the book does not go step by step explaining the code and all the concepts. Please refer to the detailed source code notebooks for details of the implementation. The code snippets given in the book cover the core logic and often skip introductory steps like setting up a library or importing a package as they are covered in the associated notebooks. To cover the wide range of concepts the book provides more than 450 extensive references to delve deeper into these topics. This book will be a day-to-day cookbook giving you a pragmatic view while building any NLP system as well as be a stepping stone to broaden the application of NLP into your domain.

Please note that readers pursuing cutting-edge research in NLP may find some sections of the book rudimentary as it does not cover in-depth theoretical and technical details related to NLP concepts. Moreover, it is expected that the readers will follow the respective documentations for various frameworks used in the code examples.