Название: Natural Language Processing in the Real World: Text Processing, Analytics, and Classification
Автор: Jyotika Singh
Издательство: CRC Press
Год: 2023
Страниц: 393
Язык: английский
Формат: pdf (true)
Размер: 25.6 MB

Natural Language Processing in the Real World is a practical guide for applying data science and machine learning to build Natural Language Processing (NLP) solutions. Where traditional, academic-taught NLP is often accompanied by a data source or dataset to aid solution building, this book is situated in the real world where there may not be an existing rich dataset.

This book covers the basic concepts behind NLP and text processing and discusses the applications across 15 industry verticals. From data sources and extraction to transformation and modelling, and classic Machine Learning to Deep Learning and Transformers, several popular applications of NLP are discussed and implemented.

Natural Language Processing (NLP) is a hot topic with a lot of applications and an increasing amount of research across the globe. NLP refers to a machine’s process to understand language. With the immense amount of text data generated today, there is an increase in the scope for leveraging NLP to build intelligent solutions. Google Trends suggests a 112% increase in searches on the topic of Natural Language Processing in the past seven years. Many businesses today offer products and services powered by NLP. Common examples include Amazon Alexa, Gmail sentence auto-completion, and Google Translate for language translation. With the increasing demand for NLP-based products and services, there is a strong need for a workforce that is able to understand and implement NLP solutions.

This book starts by introducing NLP, underlying concepts, and popular tools. Then, the book dives into everything around data – data curation, data extraction, and data storage. The data needs to be cleaned and converted to a language that a machine can understand. The book implements several data preprocessing methods, data transformation methods, distance metrics, Machine Learning, Deep Learning, and transformers. In a practical sense, businesses make use of the technique that best solves their use case, including classic/traditional models and state-of-the-art models. This book covers them all through a practical lens. With the knowledge about data and models, you are ready to put it together to build NLP applications. But what are these NLP applications, who uses them, and for what? This book dives into NLP applications across 15 industry verticals. Then, we pick the most commonly used applications and implement them in many different ways using Python and various open-source tools. Then, this book describes NLP projects in the real world, in an actual business setting. Why do you decide to build an NLP-based project? How do you measure success? Where does it fit into your company’s goals? How is the model then consumed by other users and applications? All these aspects are discussed, and these NLP projects are implemented using Python and the knowledge gained from the previous sections of the book.

Who this book is for?
This book is an ideal resource for those seeking to expand their knowledge of NLP and develop practical NLP solutions. Whether you are new to NLP, seeking to deepen your understanding, or exploring NLP for a specific use case, this book caters to all levels of expertise. By emphasizing practical applications of NLP and providing insights into how more than 15 industry verticals leverage NLP, this book offers valuable guidance for those looking to develop their own solutions using text data.

But how would you go about it? What sets this book apart is its focus on implementation. With numerous real-world NLP applications and projects using open-source tools and the Python programming language, readers will gain hands-on experience and be able to apply the solutions in your work. Readers will be able to learn the concepts and refer back to the book any time they need to brush up on their understanding of NLP usage and applications across industry verticals. Assuming the reader has a basic understanding of Machine Learning and programming in Python, this book focuses on practical aspects of NLP, covering the basic concepts from a practical perspective, rather than diving into detailed architectures. As such, this book is set to be a valuable resource for anyone looking to develop practical NLP solutions.

The solutions we build involve using classic Machine Learning approaches, Deep Learning models, and transformers, covering everything from the basics to the state-of-the-art solutions that are used by companies for building real-world applications.