Course Information

LING 575: Seminar on Statistical Machine Translation

Spring 2011


Class Information


Instructors: Kristina Toutanova and Chris Quirk (cquirk (AT) uw (DOT) edu)
Time: Mondays 4:30pm to 6:50pm LOW 202


Course Description
 

Foundations of statistical machine translation: models and algorithms. Topics include word alignment, phrasal and syntactic machine translation models, decoding algorithms, discriminative training, and some advanced specialized techniques. Coursework includes written assignments, implementation of simple translation components, experimentation with existing MT software,  and term projects.


Course Objectives

  • to teach the foundations of state-of-the-art statistical MT systems, providing the necessary background to understand current research articles in the field.
  • to give students the opportunity to experiment with MT systems and conduct a small research study in the area.




 

Prerequisites
Background in Natural Language Processing and Machine Learning. Prerequisite coursework: LING 570, LING 571, and LING 572,  CSE 574 , or permission of instructors.

Programming: basic unix/linux commands and some high-level programming language

Textbook

The main textbook is Statistical Machine Translation by Philipp Koehn. Online research papers will be used as well either to supplement or substitute material from the book.

Grading

60% - four homework sets, 40% - term project or paper.

Announcements

No announcements

Send questions about this workspace to KRISTINA TOUTANOVA.