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 aims 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 is 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 is a realistic evaluation scenario that takes into account real-world needs of the industry partners rather than being based on relatively arbitrary machine accessible criteria. It will serve as a much more reliable basis for scientific progress than the currently available and widely used procedures.

The TaraXÜ consortium consists of leading partners of Berlin-based research and industry.

Project financed by TSB Technologiestiftung Berlin – Zukunftsfonds Berlin, co-financed by the European Union – European fund for regional development.