Book excerpts:

The major focus of this book, as of the field to which it provides an introduction, is on the processing of the orthographic forms of natural language utterances and text. No attempt is made to provide serious coverage of issues in speech production and recognition. Most of the book deals with the parsing and understanding of natural language, much less on the production of it. This bias reflects the present shape of the field, and of the state of knowledge. Although there is no chapter devoted to production (= language generation) as such, some discussion of it is interleaved with that on parsing and understanding.

The book is formally oriented and technical in character, and organized, for the most part, around formal techniques. The perspective adopted is that of computer science, not cognitive science. This book has no claims to make about the way the human mind processes natural language. It concentrate on areas that are beginning to be well understood, and for which standard techniques (such as chart parsing) have begun to emerge. An inevitable consequence of this emphasis is that this book spends a good deal more time on syntactic processing than on semantic or pragmatic processing. Another consequence is that discussion of developments at the leading edge of NLP research, on such topics as parallel parsing algorithms, the new-style categorial grammars, connectionist approaches, or the emerging implementations of situation semantics and discourse representation theory, are excluded altogether or relegated to the further reading sections.

Intended Audience:

This book is aimed at computer scientists and linguists at undergraduate, postgraduate, or faculty level, who have taken, or are concurrently taking, a programming course in Prolog. However, a good proportion of the book will also be useful to people with an interest in linguistics or natural language processing (NLP) but who do not have a computational background. The book is specifically intended to teach natural language processing and computational linguistics: it does not attempt to teach programming or computer science to linguists or to provide more than an implicit introduction to linguistics for computer scientists. It is difficult to discuss a topic like NLP without assuming that one's readers have some familiarity with the rudiments of set theory (the notions of set, set membership, the subset relation, and so on), likewise the rudiments of elementary logic (negation, conjunction, disjunction, the material conditional and biconditional, existential and universal quantification, and so on). So this book makes this assumption.