Foundations of Statistical Natural Language Processing

Statistical approaches to processing natural language text have becomedominant in recent years. This foundational text is the first comprehensiveintroduction to statistical natural language processing (NLP) to appear. The bookcontains all the theory and algorithms needed for building NLP tools. It providesbroad but rigorous coverage of mathematical and linguistic foundations, as well asdetailed discussion of statistical methods, allowing students and researchers toconstruct their own implementations. The book covers collocation finding, word sensedisambiguation, probabilistic parsing, information retrieval, and otherapplications.