Machine Translation
Its Scope and Limits
Book
Hardback
300 pages
978-0-521-64367-2 (ISBN)
Description
Machine translation (MT) systems are used to the benefit of many people and organizations worldwide. However, so far an indisputably accurate, high-quality and fully-automatic MT system is yet to be produced, leading to suggestions that such an achievement is impossible. Machine Translation: Its scope and Limits is a collection of essays by Yorick Wilks on the past, present and future of MT, in which he argues against this claim. His discussion of MT's past is centred around the 'Artificial Intelligence' approach, and he explains the present day situation by highlighting current issues in MT, such as the application of linguistic resources and theories, IBM's statistical approach, and research into MT undertaken by the US Government in 1990. The book's final section discusses new models such as a pragmatics-based MT, sense projection and lexical tuning, and their place in the future of MT as both a discipline and a commercial enterprise.
More details
Series
Language
English
Place of publication
Cambridge
United Kingdom
Target group
Professional and scholarly
College/higher education
Illustrations
Worked examples or Exercises
ISBN-13
978-0-521-64367-2 (9780521643672)
Copyright in bibliographic data is held by Nielsen Book Services Limited or its licensors: all rights reserved.
Schweitzer Classification
Person
Yorick Wilks is Professor of... in the Department of Computer Science, University of Sheffield
Content
1. Introduction: the state of play in 2002; Part I. MT Past: 2. The origins of MT and its relationship to artificial intelligence; 3. An artificial intelligence approach to MT; 4. It works, but how far can it go: evaluating the SYSTRAN MT system; Part II. MT Present 5. Where am I coming from: the issue of directionality in MT; 6. Interlinguas for MT and natural languages; 7. Stone soup and the French Room: the statistical approach to MT at IBM; 8. The revival of US Government MT research in 1990; 9. The role of linguistic knowledge resources in Japanese MT; Part III. MT future: 11. Senses and texts; 12. Sense projection; 13. Lexical tuning; 14. What would pragmatics-based MT be like?; 15. Where are we now in MT: what works and what doesn't?; 16. The future of MT in the new millennium.