- Hardcover: 446 pages
- Publisher: Cambridge University Press; 1 edition (January 18, 2010)
- Language: English
- ISBN-10: 9780521874151
- ISBN-13: 978-0521874151
- ASIN: 0521874157
- Product Dimensions: 6.7 x 1 x 9.6 inches
- Shipping Weight: 2 pounds (View shipping rates and policies)
- Average Customer Review: 5 customer reviews
- Amazon Best Sellers Rank: #1,253,730 in Books (See Top 100 in Books)
Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
Statistical Machine Translation 1st Edition
Use the Amazon App to scan ISBNs and compare prices.
Frequently bought together
Customers who bought this item also bought
"Philipp Koehn has provided the first comprehensive text for this rapidly growing field of statistical machine translation. This book is an invaluable resource for students, researcher, 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, Microsoft Research
"This is an excellent introduction for someone interested in statistical translation. It is quite readable..."
Jeffrey Putnam, Computing Reviews
This class-tested text establishes background in NLP and statistics, then develops the basics through to current research. By the end readers can build their own translation systems. For advanced undergraduates in computer science, graduate students in computer science and computational linguistics, and researchers in NLP; for instruction or self-study.
Try the Kindle edition and experience these great reading features:
Showing 1-5 of 5 reviews
There was a problem filtering reviews right now. Please try again later.
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.
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.