Machine Translation Its Scope and Limits [Paperback]

A history of machine translation (MT) from the point of view of a major writer and innovator in the field is the subject of this book. It details the deep differences between rival groups on how best to do MT, and presents a global perspective covering historical and contemporary systems in Europe, the US and Japan. The author considers MT as a fundamental part of Artificial Intelligence and the ultimate test-bed for all computational linguistics.

Machine Translation (MT) is both an engineering technology and a measure of all things to do with languages and computerswhenever a new theory of language or linguistics is offered, an important criteria for its success is whether or not it will improve machine translation.

This book presents a history of machine translation (MT) from the point of view of a major writer and innovator in the subject. It describes and contrasts a range of approaches to the challenges and problems of this remarkable technology by means of a combination of historic papers along with commentaries to update their significance, both at the time of their writing and now. This volume chronicles the evolution of conflicting approaches to MT towards a somewhat skeptical consensus on future progress. Also included is a discussion of the most recent developments in the field and prospects for the future, which have been much changed by the arrival of the World Wide Web.

MT Past.- Five Generations of MT.- An Artificial Intelligence Approach to Machine Translation.- It Works but How Far Can It Go: Evaluating the SYSTRAN MT System.- MT Present.- Where Am I Coming From: The Reversibility of Analysis and Generation in Natural Language Processing.- What are Interlinguas for MT: Natural Languages, Logics or Arbitrary Notations?.- Stone Soup and the French Room: The Statistical Approach to MT at IBM.- The Revival of US Government MT Research in 1990.- The Role of Linguistic Knowledge Resources in MT.- Thelc)