Reference Texts for CS 175

CS 175, Winter 2022

Below are links to some online textbooks that should be very useful as background reading for your projects. You do not need to read all of these, but should find them for very useful as a starting point for finding relevant material on a particular text analysis topic.

• Speech and Language Processing (3rd ed draft) by Dan Jurafsky and James Martin. Highly recommended! This is an online draft of a not-yet-finished book, written by two of the top experts in natural language processing. The chapters in this book will help you understand the principles and foundational ideas behind modern NLP methods. Particularly relevant chapters for CS 175 projects include Chapter 3 on N-grams and Language Modeling, Chapters 4 and 20 on Sentiment Prediction, Chapters 6, 7, and 9 on Embedding and Deep Learning for Text, Chapter 23 on Question Answering, and Chapter 24 on Chatbots and Dialog Systems.


• Natural Language Processing with PyTorch by Delip Rao and Brian McMahan, O'Reilly Media, 2019. Note that you need to login using your UCINetID to get online access via the UCI Libraries and the publisher (O Reilly) to this text. This online text is a useful reference on how to use PyTorch for NLP applications - likely to be helpful for your projects in terms of ideas and examples. Jupyter notebooks for this book are also available online.


• The NLTK book (online). (NLTK = Natural Language Toolkit). Everything you need to know about NLTK. See also the NLTK online documentation.