This is the first exhaustive investigation of gradience in syntax, conceived of as grammatical indeterminacy. It looks at gradience in English word classes, phrases, clauses and constructions, and examines how it may be defined and differentiated. Professor Aarts addresses the tension between linguistic concepts and the continuous phenomena they describe by testing and categorizing grammatical vagueness and indeterminacy. He considers to what extent gradience is a grammatical phenomenon or a by-product of imperfect linguistic description, and makes a series of linked (...) proposals for its theoretical formalization.Bas Aarts draws on, and reviews, work in psychology, philosophy and language from Aristotle to Chomsky., and writes clearly on a fascinating and important aspect of language and cognition. His book will appeal to scholars and graduate students of language and syntactic theory in departments of linguistics, philosophy and cognitive science. (shrink)

first-order HMM, the current tag t0 is predicted based on the previous tag t−1 (and the current word).1 The back- We present a new part-of-speech tagger that ward interaction between t0 and the next tag t+1 shows demonstrates the following ideas: (i) explicit up implicitly later, when t+1 is generated in turn. While unidirectional models are therefore able to capture both use of both preceding and following tag con-.

Statistical approaches to processing natural language text have become dominant in recent years. This foundational text is the first comprehensive introduction to statistical natural language processing to appear. The book contains all the theory and algorithms needed for building NLP tools. It provides broad but rigorous coverage of mathematical and linguistic foundations, as well as detailed discussion of statistical methods, allowing students and researchers to construct their own implementations. The book covers collocation finding, word sense disambiguation, probabilistic parsing, information retrieval, (...) and other applications. (shrink)