31 August 2007

Congratulations to Bart Mellebeek who successfully defended his thesis and will be awarded the degree of PhD.

The title of Bart's thesis is "TransBooster: Black Box Optimisation of Machine Translation Systems".

He completed his PhD in the National Centre for Language Technology and the School of Computing, DCU under the supervision of Professor Andy Way and Professor Josef van Genabith.

Brief description of Project:

TransBooster is a new and modular approach to help Machine Translation (MT) systems improve their output quality by reducing the number of complexities in the input. Instead of trying to reinvent the wheel by proposing yet another approach to MT, we build on the strengths of existing MT paradigms while trying to remedy their shortcomings as much as possible. TransBooster is a wrapper technology that operates on top of an existing MT system. It reduces the complexity of the input text by a recursive decomposition algorithm which produces simple input chunks that are spoon-fed to the baseline MT system. In other words, TransBooster guides the baseline MT system through the input text and tries to help the system to improve the quality of its own translations through automatic complexity reduction. TransBooster has been successfully tested on baseline MT systems of different characteristics (Rule-based, Example-based and Statistical baseline systems) and was extended to be used as promising alternative to current Multi-Engine MT techniques.

This project was generously funded by Enterprise Ireland.

Back to News Headlines