Foundations of Statistical Natural Language Processing by Christopher D. Manning and Hinrich Schütze is a comprehensive textbook that covers a wide range of topics in statistical natural language processing (NLP). Published in 1999, it is the first textbook on the subject since Eugene Charniak's Statistical Language Learning in 1993. The book is ambitious in scope, providing a thorough introduction to probability and information theory, linguistic concepts, and empirical work. It also covers traditional tools of the trade, such as Markov models, probabilistic grammars, supervised and unsupervised classification, and the vector-space model. The book also includes chapters on specific problems in NLP, such as lexicon acquisition, word sense disambiguation, parsing, machine translation, and information retrieval. The book is structured in a way that allows for a flexible approach to learning, with topics presented in a need-to-know basis. However, the lack of an underlying set of principles driving the presentation has the unfortunate consequence of obscuring some important connections. For example, classification is not treated in a unified way, and some important techniques are deferred to later chapters. The level of mathematical detail fluctuates in certain places, and some derivations that would provide crucial motivation and clarification have been omitted. The book also occasionally exhibits excessive reluctance to extract principles, such as in its treatment of the work of Chelba and Jelinek. Despite these shortcomings, the book is a comprehensive reference for statistical NLP, and it is likely that there is a thinner book, similar to the current volume but with a background-theory-applications structure, struggling to get out. The authors are to be commended for their efforts, and the book is a valuable resource for researchers and students in the field.Foundations of Statistical Natural Language Processing by Christopher D. Manning and Hinrich Schütze is a comprehensive textbook that covers a wide range of topics in statistical natural language processing (NLP). Published in 1999, it is the first textbook on the subject since Eugene Charniak's Statistical Language Learning in 1993. The book is ambitious in scope, providing a thorough introduction to probability and information theory, linguistic concepts, and empirical work. It also covers traditional tools of the trade, such as Markov models, probabilistic grammars, supervised and unsupervised classification, and the vector-space model. The book also includes chapters on specific problems in NLP, such as lexicon acquisition, word sense disambiguation, parsing, machine translation, and information retrieval. The book is structured in a way that allows for a flexible approach to learning, with topics presented in a need-to-know basis. However, the lack of an underlying set of principles driving the presentation has the unfortunate consequence of obscuring some important connections. For example, classification is not treated in a unified way, and some important techniques are deferred to later chapters. The level of mathematical detail fluctuates in certain places, and some derivations that would provide crucial motivation and clarification have been omitted. The book also occasionally exhibits excessive reluctance to extract principles, such as in its treatment of the work of Chelba and Jelinek. Despite these shortcomings, the book is a comprehensive reference for statistical NLP, and it is likely that there is a thinner book, similar to the current volume but with a background-theory-applications structure, struggling to get out. The authors are to be commended for their efforts, and the book is a valuable resource for researchers and students in the field.