Machine Learning for Text

by Charu C. Aggarwal

This second edition textbook covers a coherently organized framework for text analytics, which integrates material drawn from the intersecting topics of information retrieval, machine learning, and natural language processing. Particular importance is placed on deep learning methods. The chapters of this book span three broad Basic Chapters 1 through 7 discuss the classical algorithms for text analytics such as preprocessing, similarity computation, topic modeling, matrix factorization, clustering, classification, regression, and ensemble analysis. 2. Domain-sensitive learning and information Chapters 8 and 9 discuss learning models in heterogeneous settings such as a combination of text with multimedia or Web links. The problem of information retrieval and Web search is also discussed in the context of its relationship with ranking and machine learning methods. 3. Natural language Chapters 10 through 16 discuss various sequence-centric and natural language applications, 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. Compared to the first edition, this second edition textbook (which targets mostly advanced level students majoring in computer science and math) has substantially more material on deep learning and natural language processing. Significant focus is placed on topics like transformers, pre-trained language models, knowledge graphs, and question answering.

588 pages, Hardcover

Published May 5, 2022

Reviews

[A Mig · Rating 5 out of 5]

Where to start to learn about text classification and clustering. Provides practical guidance, with some nice toy examples to illustrate some of the algorithms' intricacies. The software resources, along with the bibliographical notes, were quite useful. As a plus, the quotes at the start of each chapter were spot-on.

[Aryan kamboj · Rating 5 out of 5]

Being an avid reader of Charu C. Aggarwal's books, I had to read this book. I was working on a project on Natural Language Processing when I got a chance to read this book. Needless to say, it is a classic. Unlike many other books written on the topic, Aggarwal's book stands out. The thorough explanation of even the smallest topic and "why?" of the various algorithms was very helpful, instead of just throwing the topics on the reader, the author took to things one by one, explaining the reason for why are we doing this and why we need improvement. I have read many articles and blogs on LDA and PLSA but never understood the sole reason behind the development of both. The author clearly explained why it was necessary and also made sure that the mathematical and theoretical balance remains. I managed to read the whole book in a couple of sittings. Most of the times, authors do not consider it important to include Information Retrieval as a part of Natural Language Processing, but Mr. Aggarwal included a whole chapter on Retrieval Methods. These are just a few parts of the book, in all, the whole book is an ocean of information and I would definitely recommend this book to anyone who wants to completely understand NLP and its latest advancements.