Prof. Melamed's Translation Research

'Company' Description

CS Prof. Dan Melamed designs algorithms and writes code that translates text between human languages.  See http://www.cs.nyu.edu/~melamed/interests.html for more info.  He's exploring an approach based on  structured models of translational equivalence.  His work is funded by DARPA.

Proposal: A System for collecting parallel texts from the Web

Melamed's work uses parallel texts--copies of the same document in 2 languages--to help develop and test his translation software.  
This project involves designing and building a system for collecting and processing parallel texts retrieved from the Web.  The system will work as follows:
Note that the web trawling and serving loop is very similar to what is used by "shopping agents" and price-comparison websites. 
The open design issues in this project include:
The system must be able to run on Linux.
This is a technically demanding project, that Prof. Melamed will supervise.  He's available for meetings on evenings and weekends.

Intern Address

715 Broadway

Company Web site

http://www.cs.nyu.edu/~melamed/

Authorizing manager

Prof. I. Dan Melamed

Project manager

Prof. Melamed

Resources that will be made available to students

Access to any relevant data, code and information.