Natural Language Understanding with Python: Combine natural language technology, deep learning, and large language models to create human-like language comprehension in computer systems

by Deborah A. Dahl

Build advanced NLU systems by utilizing NLP libraries such as NLTK, SpaCy, BERT, and OpenAI; ML libraries like Keras, scikit-learn, pandas, TensorFlow, and NumPy, along with visualization libraries such as Matplotlib and Seaborn.

Purchase of the print Kindle book includes a free PDF eBook

Key FeaturesMaster NLU concepts from basic text processing to advanced deep learning techniquesExplore practical NLU applications like chatbots, sentiment analysis, and language translationGain a deeper understanding of large language models like ChatGPTBook DescriptionNatural Language Understanding facilitates the organization and structuring of language allowing computer systems to effectively process textual information for various practical applications. Natural Language Understanding with Python will help you explore practical techniques for harnessing NLU to create diverse applications.

with step-by-step explanations of essential concepts and practical examples, you’ll begin by learning about NLU and its applications. You’ll then explore a wide range of current NLU techniques and their most appropriate use-case. In the process, you’ll be introduced to the most useful Python NLU libraries. Not only will you learn the basics of NLU, you’ll also discover practical issues such as acquiring data, evaluating systems, and deploying NLU applications along with their solutions. The book is a comprehensive guide that’ll help you explore techniques and resources that can be used for different applications in the future.

By the end of this book, you’ll be well-versed with the concepts of natural language understanding, deep learning, and large language models (LLMs) for building various AI-based applications.

What you will learnExplore the uses and applications of different NLP techniquesUnderstand practical data acquisition and system evaluation workflowsBuild cutting-edge and practical NLP applications to solve problemsMaster NLP development from selecting an application to deploymentOptimize NLP application maintenance after deploymentBuild a strong foundation in neural networks and deep learning for NLUWho this book is forThis book is for python developers, computational linguists, linguists, data scientists, NLP developers, conversational AI developers, and students looking to learn about natural language understanding (NLU) and applying natural language processing (NLP) technology to real problems. Anyone interested in addressing natural language problems will find this book useful. Working knowledge in Python is a must.

Table of ContentsNatural Language Understanding, Related Technologies, and Natural Language ApplicationsIdentifying Practical Natural Language Understanding ProblemsApproaches to Natural Language Understanding – Rule-Based Systems, Machine Learning, and Deep LearningSelecting Libraries and Tools for Natural Language UnderstandingNatural Language Data – Finding and Preparing DataExploring and Visualizing DataSelecting Approaches and Representing DataRule-Based TechniquesMachine Learning Part 1 - Statistical Machine LearningMachine Learning Part 2 – Neural Networks and Deep Learning TechniquesMachine Learning Part 3 – Transformers and Large Language Models&l

326 pages, Kindle Edition

Published June 30, 2023

Reviews

[Michael · Rating 5 out of 5]

Pre-Covid -- and before the current craze for GPT reached such proportions, I worked with Azure's AI studio and programmed some classifiers by hand in R (beloved by both statisticians and those who are simply Old At heart), also supervising an intern who was doing ML in Python but, beyond going through the tutorials, never had much hands-on experience with Python. So, I bought Dahl's book as a kind of refresher before reading Emily Webber's book on Pretraining & LLMs and Dennis Rothman's book on Transformers.

The book was great. The treatment of individual topics was short, complete, and sweet. Although I was familiar theoretically with almost all of the material already, it was terrific for helping me organize what I knew...and for putting it into practice specifically there inside of Jupyter Notebook. I also want to especially single out how great the in-text references are: way more than a mere bibliography, she contextualizes the problem and then suggests as a preview how the further reading will address it in advance of giving the actual reference. At least for my way of thinking about the research agenda, this worked out really well. Term definitions and distinctions were very clear. I'll continue to keep NLU w/ Python deskside while reading the next couple/few books and beginning my project.