This gentle introduction to the most important techniques in natural language processing uses a unified mathematical and algorithmic framework and gradually increases in complexity. Topics covered range from n-gram language models to large language models (LLMs), from perceptron to deep learning, from text classification to structured prediction (e.g., sequence labelling, segmentation, and parsing) and generation, and from discrete representation to neural representation of linguistics structures. This book provides a comprehensive overview of NLP, making it ideal for upper undergraduate and graduate students in computer science and a valuable reference for researchers and engineers. Exercises of varying difficulty are provided as well as teaching slides and tutorial videos. The new edition features three new chapters on pre-trained language models and large language models as well as a new preliminary chapter overviewing data and model as a framework for NLP methods.

‘With the impact of generative Large Language Models (LLMs), there is an urgent need for a modern grounding in Natural Language Processing (NLP) and Machine Learning. This book provides exactly what is needed. Its thorough and well-paced chapters follow a clearly structured sequence that has been tested in many years of courses taught by the authors. After a multi-chapter review of the essential aspects of Natural Language Processing that covers the linguistic, probabilistic, and representational necessities, it describes the principal computational learning tasks lying at the heart of NLP before moving on to Deep Learning, neural networks, and LLMs. Functioning as the basis of a 15-week course, this book includes useful exercises after each chapter. It is lucid, well-signposted, and contains many useful illustrations and tables. I cannot think of a better or more timely book on the topic.’

Eduard Hovy - University of Melbourne