Syntax-Driven Statistical Machine Translation


Automatic ("machine") translation from one language to another is one of the most difficult and most fascinating problems in computer science. Despite decades of research, and a great deal of progress, the output of machine translation (MT) systems is often incomprehensible. A number of exciting recent advances in science and engineering, along with the burgeoning information landscape, have made machine translation ripe for a leap forward. The goal of our workshop is to develop and integrate a number of new techniques in a clean and flexible framework, in order to catalyze a leap in MT quality. The workshop will be very hands-on, pushing theory into algorithms, into software, and into experimental results. All team members, junior and senior, will have strong analytical and programming skills. The diversity of topics that are relevant to MT virtually guarantees that everyone's work will match their talents and interests, while remaining part of a collegial group working towards a common goal. The ability to read a foreign language, especially French or Arabic, would be an asset, but is not mandatory.

The Center for Language and Speech Processing
The Johns Hopkins University
3400 North Charles Street, Barton Hall
Baltimore, MD 21218
*Telephone: (410) 516-4237 *Fax: (410) 516-5050 *E-mail: clsp@clsp.jhu.edu