Author Description

Computer research into the English language is forsaking its preoccupation with artificial examples in favour of statistical techniques applied to real-life usage. The research programme described in this volume has taken these techniques deeper than previously attempted. Equally important to researchers in the fields of linguistics and computer science, the book records a unique attempt over a ten-year period to use stochastic optimization in the natural language processing domain. Setting the work against the background of the logical rule-based approach, the author provides a context for understanding the differences in assumptions about the nature of language and cognition which characterized this project from the outset and which now account for the project's acknowledged contribution to the field of computational linguistics. Though necessarily involving technical language, the book is accessible to anyone with an interest in thinking about the structural aspects of language and the reader is given a sense of the process of research as a human enterprise, as well as shown its products.