Skip to main content
EN 600.468 Machine Translation
Spring 2015
Tuesdays and Thursdays 1:30-2:45
Hodson 313
Computer Science Department
Johns Hopkins University

Google translate instantly translates between any pair of over eighty human languages like French and English. How does it do that? Why does it make the errors that it does? And how can you build something better? Modern translation systems like Google Translate, Bing Translator, and SDL FreeTranslation learn to translate by reading millions of words of already translated text. This course will show you how they work. We cover fundamental building blocks from linguistics, machine learning, algorithms, data structures, and formal language theory, showing how they apply to a difficult real-word artificial intelligence problem.

Instructors
Philipp Koehn with help from Matt Post
Office hours
Wednesday 12-1, Hackermann 227
Discussion Forum
Piazza
Textbook
Statistical Machine Translation (errata) by Philipp Koehn You can read it online through the JHU library or purchase from Amazon.
Grading
To understand how machine translation works, you must build a translation system. We will mainly grade hands-on work.
  • Six homework assignments (10% each)
  • Final project (30%)
  • In-class presentation: Language in ten minutes (10%)

Resource: All slide sources