Authors:
- Addresses fundamental issues to solve the classic problems with machine translation
- Recounts the little known background of early events affecting the history of machine translation
- Identifies complexity as principal reason why machine translation has had limited success
- Illustrates problems of ambiguity and complexity in various present-day machine translation models, rule-based (RBMT), statistical (SMT) and neural MT (NMT)
Part of the book series: Machine Translation: Technologies and Applications (MATRA, volume 2)
Buy it now
Buying options
Tax calculation will be finalised at checkout
Other ways to access
This is a preview of subscription content, log in via an institution to check for access.
Table of contents (9 chapters)
-
Front Matter
-
Part I
-
Front Matter
-
-
Part II
-
Front Matter
-
About this book
This book is about machine translation (MT) and the classic problems associated with this language technology. It examines the causes of these problems and, for linguistic, rule-based systems, attributes the cause to language’s ambiguity and complexity and their interplay in logic-driven processes. For non-linguistic, data-driven systems, the book attributes translation shortcomings to the very lack of linguistics. It then proposes a demonstrable way to relieve these drawbacks in the shape of a working translation model (Logos Model) that has taken its inspiration from key assumptions about psycholinguistic and neurolinguistic function. The book suggests that this brain-based mechanism is effective precisely because it bridges both linguistically driven and data-driven methodologies. It shows how simulation of this cerebral mechanism has freed this one MT model from the all-important, classic problem of complexity when coping with the ambiguities of language. Logos Model accomplishes this by a data-driven process that does not sacrifice linguistic knowledge, but that, like the brain, integrates linguistics within a data-driven process. As a consequence, the book suggests that the brain-like mechanism embedded in this model has the potential to contribute to further advances in machine translation in all its technological instantiations.
Reviews
“Natural language processing is one of the most rapidly evolving areas of artificial intelligence, and is the subject of this excellent book. … One of the important contributions of this valuable resource is its presentation and comparison of many current state-of-the-art machine translation systems available to the general public. Summing Up: Recommended. Advanced undergraduates through faculty and professionals.” (J. Brzezinski, Choice, Vol. 56 (6), February, 2019)
Authors and Affiliations
-
Tarpon Springs, USA
Bernard Scott
Bibliographic Information
Book Title: Translation, Brains and the Computer
Book Subtitle: A Neurolinguistic Solution to Ambiguity and Complexity in Machine Translation
Authors: Bernard Scott
Series Title: Machine Translation: Technologies and Applications
DOI: https://doi.org/10.1007/978-3-319-76629-4
Publisher: Springer Cham
eBook Packages: Computer Science, Computer Science (R0)
Copyright Information: Springer International Publishing AG, part of Springer Nature 2018
Hardcover ISBN: 978-3-319-76628-7Published: 15 June 2018
Softcover ISBN: 978-3-030-09538-3Published: 28 December 2018
eBook ISBN: 978-3-319-76629-4Published: 06 June 2018
Series ISSN: 2522-8021
Series E-ISSN: 2522-803X
Edition Number: 1
Number of Pages: XVI, 241
Number of Illustrations: 55 b/w illustrations
Topics: Natural Language Processing (NLP), Computational Linguistics, Psycholinguistics