Last week we sat down with Mark Breuker from EDIA, who is a specialist in language technologies for education. Mark’s work has been an integral part of the iRead project – he has collaborated with the project through developing models with which to classify texts based on their difficulty.
Thanks for speaking with us today, Mark. Could you first introduce yourself with a few sentences, your background and the type of work you do for ELG? What interests you most working in this space?
My name is Mark Breuker, I’m the managing director of EDIA. Our company develops language technologies for education. We apply Natural Language Processing and Machine Learning to automatically analyse educational resources. This makes it possible to label these resources with subjects, learning objectives and difficulty levels. As part of iRead we’ve developed classification models to assess the reading difficulty of texts that can be used in language learning. We believe these technologies will have a transformational impact on the discoverability of suitable learning materials for every student and scalability of personalized learning applications.
And what exactly is the European Language Grid (ELG)?
The ELG is a digital marketplace on which European companies and research organisations can showcase and offer their Language Technologies to customers. The ELG develops and deploys a scalable cloud platform, providing, in an easy-to-integrate way, access to hundreds of commercial and non-commercial Language Technologies for all European languages, including running tools and services as well as data sets and resources.
Why is it important that we have a space such as ELG?
The current European Language Technology business and research landscape is very fragmented. The main objective is to address this fragmentation by establishing the ELG as the primary platform for Language Technology in Europe and to strengthen European LT business with regard to the competition from other continents. Also, language technologies are often focussed on English and a few other languages. The ELG will provide a broad coverage of offerings for all European languages, small and big, not only the ones that already enjoy good technology support.
Could you describe the type of work that ELG does with iRead?
ELG will be the main distribution platform for the language resources (e.g. dictionaries) and services that have been developed in the iRead project. One of the innovation objectives of the iRead project is to fast-track the development of technology for new industry players in the arena of literacy and language learning. Through ELG we hope to have a lasting impact towards this goal after the end of the iRead project.
How do you see ELG’s work developing in the future and the types of audiences it will serve?
Earlier this year the 2nd version of the ELG platform was released, offering new features for editing and uploading resources and services. On this platform we have published the first set of resources and services from the iRead project. Over the coming months (towards the end of the iRead project) we plan to publish the remaining resources. At the same time we will engage with SMEs and the emerging ELG community to promote the resources as part of our dissemination and incubation activities.
To learn more about the work Mark does for ELG, and insights into the platform, please navigate to the website: https://www.european-language-grid.eu. To learn more about EDIA, visit the website here: https://www.edia.nl