Foundations of Statistical Natural Language Processing

Christopher D. Manning and Hinrich Schütze

Chapter 13: Statistical Alignment and Machine Translation

• Arcade evaluation of text alignment systems in French; or in English

• The EGYPT toolkit for Statistical MT, developed during the 1999 Johns Hopkins summer workshop, largely as a reimplementation of the classic IBM Statistical MT work
• The ISI ReWrite decoder -- a search decoder that can be used with the EGYPT toolkit.
• GIZA++: A series of extensions (Models 4 and 5, tagging models, etc.) to the EGYPT Giza tool by Franz Och.
• A lot of recent statistical MT information, including a Statistical MT Tutorial Workbook can be found at Kevin Knight's homepage
• Word-aligned French/English Bible data from the Blinker project, and some documentation among Dan Melamed's publications.
• English-German and English-Spanish dictionaries
• Searchable Canadian Hansard French-English parallel texts (1986-1993). From the Laboratoire de Recherche Appliquée en Linguistique Informatique, Universite de Montréal.
• European Union web server. Parallel text in all EU languages.
• Adam Berger's software page includes Align a sentence alignment tool in C++.
• MT Archive. A general MT reference site by John Hutchins.
• MT Publications by John Hutchins