Statistical Machine Translation.pdf

This page intentionally left blank

Statistical Machine Translation

The ﬁeld of machine translation has recently been energized by the emer-

gence of statistical techniques, which have brought the dream of automatic

language translation closer to reality. This class-tested textbook, authored

by an active researcher in the ﬁeld, provides a gentle and accessible intro-

duction to the latest methods and enables the reader to build machine

translation systems for any language pair.

It provides the necessary grounding in linguistics and probabilities,

and 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 lin-

guistic annotation. The book reports on the latest research and outstanding

challenges, and enables novices as well as experienced researchers to make

contributions to the ﬁeld. It is ideal for students at undergraduate and grad-

uate level, or for any reader interested in the latest developments in machine

translation.

PHILIPP KOEHN is a lecturer in the School of Informatics at the Uni-

versity of Edinburgh. He is the scientiﬁc coordinator of the European

EuroMatrix project and is also involved in research funded by DARPA in

the USA. He has also collaborated with leading companies in the ﬁeld,

such as Systran and Asia Online. He implemented the widely used decoder

Pharaoh, and is leading the development of the open source machine

translation toolkit Moses.

Statistical Machine Translation

Philipp Koehn

School of Informatics

University of Edinburgh