Statistical Machine Translation and over 2 million other books are available for Amazon Kindle . Learn more
  • RRP: £49.99
  • You Save: £5.00 (10%)
FREE Delivery in the UK.
Only 15 left in stock (more on the way).
Dispatched from and sold by Amazon.
Gift-wrap available.
Statistical Machine Trans... has been added to your Basket
Trade in your item
Get a £14.75
Gift Card.
Have one to sell?
Flip to back Flip to front
Listen Playing... Paused   You're listening to a sample of the Audible audio edition.
Learn more
See this image

Statistical Machine Translation Hardcover – 17 Dec 2009

See all 2 formats and editions Hide other formats and editions
Amazon Price New from Used from
Kindle Edition
"Please retry"
"Please retry"
£39.02 £39.37

Frequently Bought Together

Statistical Machine Translation + Speech and Language Processing: International Version: an Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition
Price For Both: £97.98

Buy the selected items together

Trade In this Item for up to £14.75
Trade in Statistical Machine Translation for an Amazon Gift Card of up to £14.75, which you can then spend on millions of items across the site. Trade-in values may vary (terms apply). Learn more

Product details

More About the Author

Discover books, learn about writers, and more.

Product Description


'Philipp Koehn has provided the first comprehensive text for the rapidly growing field of statistical machine translation. This book is an invaluable resource for students, researchers, and software developers, providing a lucid and detailed presentation of all the important ideas needed to understand or create a state-of-the-art statistical machine translation system.' Robert C. Moore, Principal Researcher, Microsoft Research

'The book primarily represents an ideal introduction to the field of statistical machine translation, but also tackles many of the recent results in this area. It is the product of the many years of both active research and extensive teaching of the author … Each chapter is additionally endowed with a summary, further reading and exercises, achieving thus completely the proposed goal of an accessible introduction to the statistical machine translation field. Apart from its formative role for beginners, the book also stands as a complete guide for researchers in a domain of high interest and rapid expansion … For all these reasons, this book should be welcomed as a highly valuable publication.' Zentralblatt MATH

'… Statistical Machine Translation provides an excellent synthesis of a vast amount of literature (the bibliography section takes up 45 double-column pages) and presents it in a well-structured and articulate way. Moreover, the book has been class-tested and contains a set of exercises at the end of each chapter, as well as numerous references to open source tools and resources which enable the diligent reader to build MT systems for any language pair.' Target: International Journal of Translation Studies

Book Description

Automatic language translation systems like those used by Google, have been revolutionized by recent advances in the methods used in statistical machine translation. This first textbook on the topic explains these innovations carefully and shows the reader, whether a student or a developer, how to build their own translation system.

Inside This Book (Learn More)
Browse Sample Pages
Front Cover | Copyright | Table of Contents | Excerpt | Index
Search inside this book:

Customer Reviews

There are no customer reviews yet on
5 star
4 star
3 star
2 star
1 star

Most Helpful Customer Reviews on (beta) 5 reviews
10 of 10 people found the following review helpful
Gold Standard in SMT 27 Jan. 2010
By Jay Yamada - Published on
Format: Hardcover Verified Purchase
Philipp Koehn is a superb lecturer and teacher in the area of statistical machine translation (SMT). I have being living off his lecture notes from the ACL, LSA summer session and Edinburgh for years and eagerly waiting for this book to tie everything together.

Koehn has the ability to take complex statistical concepts and make them comprehensible. And he has an encyclopedic knowledge of the state-of-the-art in SMT. His bibliography alone is worth the price of this book.

This book will be the gold standard in SMT for years to come. I would highly recommend to students and professionals in the field.
5 of 5 people found the following review helpful
Must-Have Item for MT System Developer 30 Sept. 2010
By Sunghyun Kim - Published on
Format: Hardcover Verified Purchase
I currently work at NLP software company in South Korea as an NLU software developer.
When I bought this book, I was finishing my own MT decoder and starting to
build a rudimentary IBM word alignment model trainer.

This book greatly contributed to the project in that it deeply corrected my wrong understanding of
many concepts such as dynamic programming, optimization, beam search, and etc.

Best part : It includes easy-to-understand pseudo-code for IBM 1~5 word alignment process.

It was also helpful in improving the performance of existing decoder.

As one of the leading figures in well-known Moses project and Euro Matrix,
author's explanation is firmly grounded upon practical experience and
includes a lot of elements required for building a prototype MT system.

I believe reading this book with the background knowledge
that you can learn in such books as Artificial Intelligence
: A Modern Approach or Mitchell's Machine Learning,
may maximize your learning rate, since the subject stuffs in
these books are highly inter-related with each others,
for example, unsupervised learning algorithm(especially EM),
optimization and search.

This book is top-ranked in NLP category of my personal book shelf.
I guess you won't regret if you purchase one.
Must-have for all scientists working on SMT 19 Nov. 2014
By Tommi Pirinen - Published on
Format: Kindle Edition Verified Purchase
It is more or less obligatory reading for anyone working on the topic. Goes through most important methods and approaches to implementing the system and the algorithms are described well enough that one can re-implement them easily. There are some errors that can be problematic if you forget to check the errata. Sometimes the notations of formulas are a bit hard to follow. All in all rather well written school-book for contemporary statistical machine translation.
enjoyed the kindle edition 18 Aug. 2013
By richard scott - Published on
Format: Kindle Edition Verified Purchase
well written and entertaining text book. would have liked more on hierarchical parsing models. the kindle edition was great except that the diagrams could not be zoomed
0 of 1 people found the following review helpful
Now I know what is SMT 29 Oct. 2013
By Anatoly CHEONG - Published on
Format: Hardcover Verified Purchase
Excellent Book in English wIth brain neutral explanation. Not too much alien symbols. Great thanx to the author. Really good book.!
Were these reviews helpful? Let us know