петък, 17 юли 2009 г.

Getting SMART

More than half of the EU citizens are not able to hold a conversation in a language other than their mother tongue, let alone to conduct a negotiation, or interpret a law. In a time of wide availability of communication technologies, language barriers are a serious bottleneck to European integration and to economic and cultural exchanges in general. More effective tools to overcome such barriers, in the form of software for machine translation and other cross-lingual textual information access tasks, are in strong demand.

SMART is a 3-year "Specific Target Research Project" (STReP) funded by the European Commission through its "Information Society Technologies" (IST) priority, as part of the sixth Framework Programme. It started on October 1, 2006. SMART combines Statistical Learning, Machine Translation and Textual Information Access in order to create new software for machine translation and other cross-lingual textual information access tasks that will be much more reliable than the existing solutions and promises that the project "will ensure that advances make their way out of the laboratories, in the form of both significant and measurable improvements over existing technologies and of new applications currently beyond the state of the art".

Here is a deliverable of theirs that interests everyone who works with CAT applications:

Online Learning Algorithms for Computer- Assisted Translation - SMART consortium
And here's a video, presenting Online learning for CAT applications by Nicolò Cesa-Bianchi