A Statistical Machine Translation Primer
Nicola Cancedda, Marc Dymetman, George Foster, Cyril Goutte
This first chapter is a short introduction to the main aspects of Statistical Machine Translation. In particular, we cover the issues of automatic evaluation of Machine Translation output, language modelling, word-based and phrase-based translation models, and the use of syntax in Machine Translation. We will also do a quick round-up of some more recent directions that we believe may gain importance in the future. We put this in the general context of Machine Learning research, and put the emphasis on similarities and differences with standard Machine Learning problems and practice.
Introduction to the Volume « Learning Machine Translation »,