Wow! eBook
Machine Learning Techniques for Text: Apply modern techniques with Python for text processing, dimensionality reduction, classification, and evaluation
Author(s): Nikos Tsourakis (Author)
- Publisher: Packt Publishing
- Publication Date: 31 Oct. 2022
- Language: English
- Print length: 448 pages
- ISBN-10: 1803242388
- ISBN-13: 9781803242385
Book Description
Take your Python text processing skills to another level by learning about the latest natural language processing and machine learning techniques with this full color guide
Key Features
- Learn how to acquire and process textual data and visualize the key findings
- Obtain deeper insight into the most commonly used algorithms and techniques and understand their tradeoffs
- Implement models for solving real-world problems and evaluate their performance
Book Description
With the ever-increasing demand for machine learning and programming professionals, it’s prime time to invest in the field. This book will help you in this endeavor, focusing specifically on text data and human language by steering a middle path among the various textbooks that present complicated theoretical concepts or focus disproportionately on Python code.
A good metaphor this work builds upon is the relationship between an experienced craftsperson and their trainee. Based on the current problem, the former picks a tool from the toolbox, explains its utility, and puts it into action. This approach will help you to identify at least one practical use for each method or technique presented. The content unfolds in ten chapters, each discussing one specific case study. For this reason, the book is solution-oriented. It’s accompanied by Python code in the form of Jupyter notebooks to help you obtain hands-on experience. A recurring pattern in the chapters of this book is helping you get some intuition on the data and then implement and contrast various solutions.
By the end of this book, you’ll be able to understand and apply various techniques with Python for text preprocessing, text representation, dimensionality reduction, machine learning, language modeling, visualization, and evaluation.
What you will learn
- Understand fundamental concepts of machine learning for text
- Discover how text data can be represented and build language models
- Perform exploratory data analysis on text corpora
- Use text preprocessing techniques and understand their trade-offs
- Apply dimensionality reduction for visualization and classification
- Incorporate and fine-tune algorithms and models for machine learning
- Evaluate the performance of the implemented systems
- Know the tools for retrieving text data and visualizing the machine learning workflow
Who this book is for
This book is for professionals in the area of computer science, programming, data science, informatics, business analytics, statistics, language technology, and more who aim for a gentle career shift in machine learning for text. Students in relevant disciplines that seek a textbook in the field will benefit from the practical aspects of the content and how the theory is presented. Finally, professors teaching a similar course will be able to pick pertinent topics in terms of content and difficulty. Beginner-level knowledge of Python programming is needed to get started with this book.
Table of Contents
- Introducing Machine Learning for Text
- Detecting Spam Emails
- Classifying Topics of Newsgroup Posts
- Extracting Sentiments from Product Reviews
- Recommending Music Titles
- Teaching Machines to Translate
- Summarizing Wikipedia Articles
- Detecting Hateful and Offensive Language
- Generating Text in Chatbots
- Clustering Speech-to-Text Transcriptions
Editorial Reviews
Review
“The book presents a perfect amalgamation of NLP and machine learning techniques for developing practical applications dealing with unstructured text data. Each chapter of this book is carefully designed around practical applications. Despite so much content on NLP and ML available online, this book would be my first choice for learning or revising any concept involving both NLP and ML.”
—
Aditya Bhattacharya, Explainable AI Researcher, KU Leuven
“As AI professionals, we often get lost in the latest LLM architectures, forgetting that text data is the base of human communication. This book explains foundational NLP concepts clearly and thoroughly, which are essential for understanding how LLMs solve real-world business issues.
Why I liked this book:
- Step-by-step approach with clear illustrations and examples (in Python)
- Explains the utility of each technique and method, presents practical use cases, and then delves into implementation, contrasting various solutions
- Solution-oriented with case studies, many of which have high business relevancy
Key takeaways:
- Fundamental concepts of ML for text
- Text data representation and embeddings
- Foundational concepts behind LLMs like transformers and attention mechanisms
- Text preprocessing techniques and their trade-offs
- Dimensionality reduction for visualization and classification
- Fine-tuning algorithms and models for textual ML
- Evaluating the performance of implemented systems
- Tools for retrieving text data and visualizing the ML workflow
Who is it for?
Practitioners and managers of data analytics, data science, and data engineering, and students and professors in relevant disciplines. A beginner-level knowledge of Python programming is needed.
NLP and ML for text are pivotal in today’s AI-driven world, especially with the great attention given to GenAI and LLMs these days. This book does not just chase the latest sexy trends but enables readers to understand and master the foundational concepts. Highly recommended reading.”
—
Andrea De Mauro, Executive Data & AI Advisor, Author of “Data Analytics Made Easy”, Former Data Executive at Vodafone and P&G
About the Author
Nikos Tsourakis is a professor of computer science and business analytics at the International Institute in Geneva, Switzerland, and a research associate at the University of Geneva. He has over 20 years of experience designing, building, and evaluating intelligent systems using speech and language technologies. He has also co-authored over 50 research publications in the area. In the past, he worked as a software engineer, developing products for major telecommunication vendors. He also served as an expert for the European Commission and is currently a certified educator at the Amazon Web Services Academy. He holds a degree in electronic and computer engineering, a master’s in management, and a PhD in multilingual information processing.
