Project

taraXÜ

Self-Adapting Machine Translation with Multi-Approach Language Technology

Self-Adapting Machine Translation with Multi-Approach Language Technology

After a period where Machine Translation (MT) seemed to have reached a plateau, recent advances in Language Technology (LT) as well as a rising need for translation services have provided new momentum for research and development in this direction. TaraXÜ aimed at comparative study and parallelization of current major LT and MT paradigms (Pattern-based, Rule-based, Statistical, and using Translation Memories). As it has been observed that the systems tend to make different errors, the main goal of the project was to design an informed selection mechanism that

  • leads to better overall translation results,
  • helps improve individual systems, and
  • provides new scientific insights, especially in the context of statistical processing.

A key ingredient of taraXÜ was a realistic evaluation scenario that took into account real-world needs of the industry partners rather than being based on relatively arbitrary machine accessible criteria. It may serve as a much more reliable basis for scientific progress than the currently available and widely used procedures.

A list of taraXÜ publications can be found here.

Partners

acrolinx
acrolinx
euroscript systems
euroscript
yocoy
yocoy

Share project:

Contact Person
Dr. phil. Aljoscha Burchardt

Publications about the project

Eleftherios Avramidis, Aljoscha Burchardt, Sabine Hunsicker, Maja Popovic, Cindy Tscherwinka, David Vilar Torres, Hans Uszkoreit

In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14). International Conference on Language Resources and Evaluation (LREC-14) May 26-31 Reykjavik, Iceland Iceland Pages 2679-2682 ISBN 978-2-9517408-8-4 European Language Resources Association (ELRA) 5/2014.

To the publication

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz