The dream of automatic language translation is now closer thanks to recent advances in the techniques that underpin statistical machine translation. This class-tested textbook from an active researcher in the field, provides a clear and careful introduction to the latest methods and explains how to build machine translation systems for any two languages. It introduces the subject's building blocks from linguistics and probability, then covers the major models for machine translation: word-based, phrase-based, and tree-based, as well as machine translation evaluation, language modeling, discriminative training and advanced methods to integrate linguistic annotation. The book also reports the latest research, presents the major outstanding challenges, and enables novices as well as experienced researchers to make novel contributions to this exciting area. Ideal for students at undergraduate and graduate level, or for anyone interested in the latest developments in machine translation.
• The first introductory guide to this burgeoning field - takes readers step by step through theory and methods • Class tested by the author at universities and conference tutorials • Accompanying website provides additional exercises and links to further resources
Preface; Part I. Foundations: 1. Introduction; 2. Words, sentences, corpora; 3. Probability theory; Part II. Core Methods: 4. Word-based models; 5. Phrase-based models; 6. Decoding; 7. Language models; 8. Evaluation; Part III. Advanced Topics: 9. Discriminative training; 10. Integrating linguistic information; 11. Tree-based models; Bibliography; Author index; Index.
'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