Bilkent University
Department of Computer Engineering
S E M I N A R

 

  Example Based Machine Translation with Type Supported Translation Templates

 

Hande Dogan
MSc.Student
Computer Engineering
Bilkent University

Example based machine translation is a translation technique that leans on machine learning paradigm. This technique had been modeled by the learning process as: system is given short and simple sentences in language A with their correspondences in language B; it memorizes these pairs and then becomes able to translate new sentences via these pairs in the memory. In this system the translation pairs are kept as translation templates. A translation template is induced from given two translation examples by replacing differing parts in these examples by variables. A variable replacing a difference that consists of two differing parts (one from the first example, and the other one from the second example) is a generalization of those two differing parts and these variables are supported with part-of-speech tag information in order to deteriorate incorrect translations. After the learning phase, translation is achieved by finding the appropriate template(s) and replacing the variables.

 

DATE: February 27, 2006, Monday@ 15:40
PLACE: EA 409