Posted: 08/03/19
An ADAPT led project has received a funding award of over €1.15 million euro under the European Commission’s Innovation and Networks Executive Agency (INEA). The award was the largest portion of a conglomerate fund towards the development of Machine Translation across Europe. Professor Andy Way of DCU’s School of Computing and Deputy Director of the ADAPT Centre, will lead the project, PRINCIPLE, “Providing Resources in Irish, Norwegian, Croatian and Icelandic for the Purposes of Language Engineering.” This project will collaborate with Iconic Machine Translation, the National Library of Norway, the University of Zagreb, and the University of Iceland.
Speaking about PRINCIPLE, Professor Andy Way said, “The PRINCIPLE project which I’m coordinating will significantly improve MT quality for a number of low-resource languages: Irish, Norwegian, Croatian and Icelandic. We will convince public bodies to make freely available parallel data they have for these languages and English (or other languages), which can be used as additional training data for MT engines and thus improve translation quality for public administrations who wish to benefit from advances in neural MT.”
The project plans to commence this summer and will work closely with government officials in Croatia, Iceland, Ireland and Norway to ensure that the technology is fulfilling all of their linguistic and translation needs.
The grant was awarded under the recent Connecting Europe Facility (CEF) call as part of the ELRC Network (European Language Resource Co-ordination) which manages, maintains and coordinates the relevant language resources in all official languages of the EU and CEF associated countries. These activities will help to improve the quality, coverage and performance of automated translation solutions in the context of current and future CEF digital services.
The CEF proposed the grant with an original list consisting of 35 separate projects. The European Commission responded by granting more than €10.3 million towards 17 projects — 5 projects of which work specifically with Automated Translation.
Share this article:
