Machine Learning for Text

This second edition textbook provides a comprehensive framework for text analytics, integrating material from information retrieval, machine learning, and natural language processing. It emphasizes deep learning methods and covers basic algorithms, domain-sensitive learning, and natural language processing applications. The textbook is designed for advanced level students majoring in computer science and math and has more material on deep learning and natural language processing than the first edition.

Format: Paperback / softback
Length: 565 pages
Publication date: 06 May 2023
Publisher: Springer Nature Switzerland AG

This second edition textbook offers a comprehensive and coherent framework for text analytics, drawing from the intersecting domains of information retrieval, machine learning, and natural language processing. It emphasizes the use of deep learning methods, particularly in addressing complex text analysis challenges. The book is organized into three broad categories:

Basic Algorithms: Chapters 1 through 7 delve into classical text analytics algorithms, including preprocessing, similarity computation, topic modeling, matrix factorization, clustering, classification, regression, and ensemble analysis. These algorithms serve as foundational tools for text mining and provide a solid understanding of text data manipulation.

Domain-Sensitive Learning and Information Retrieval: Chapters 8 and 9 explore learning models in diverse settings, such as text combined with multimedia or Web links. The focus is on developing models that can effectively handle heterogeneous data and address information retrieval and Web search problems within the context of ranking and machine learning methods.

Natural Language Processing: Chapters 10 through 16 cover a wide range of sequence-centric and natural language applications. These chapters discuss topics such as feature engineering, neural language models, deep learning, transformers, pre-trained language models, text summarization, information extraction, knowledge graphs, question answering, opinion mining, text segmentation, and event detection. The second edition of this textbook expands significantly on deep learning and natural language processing, providing in-depth coverage of these emerging areas. It emphasizes the use of transformers, pre-trained language models, knowledge graphs, and question answering, which are crucial for modern text analysis tasks.

Designed for advanced-level students majoring in computer science and math, this textbook offers a comprehensive and up-to-date introduction to text analytics. It provides a solid foundation for those seeking to apply cutting-edge techniques in their research and practical applications. With its clear explanations, extensive examples, and practical applications, this textbook is an invaluable resource for students, researchers, and practitioners in the field of text analytics.

Weight: 1112g
Dimension: 254 x 178 (mm)
ISBN-13: 9783030966256
Edition number: 2nd ed. 2022