National Language Technology Platform (NLTP): overall view

National Language Technology Platform (NLTP): Overall View Artūrs Vasiļevskis Tilde, Riga, Latvia arturs.vasilevskis@tilde.com Jānis Ziediņš Culture Information Systems Centre, Riga, Latvia janis.ziedins@kis.gov.lv Marko Tadić University of Zagreb, Faculty of Humanities and Social Sciences, Zagreb, Croatia marko.tadic@ffzg.hr Željka Motika Central State Office for the Development of Digital Society, Zagreb, Croatia Zeljka.Motika@rdd.hr Mark Fishel University of Tartu, Tartu, Estonia fishel@ut.ee Hrafn Loftsson, Jón Guðnason Reykjavik University, School of Technology, Reykjavik, Iceland {hrafn, jg}@ru.is Claudia Borg University of Malta, Valletta, Malta claudia.borg@um.edu.mt Keith Cortis, Judie Attard Malta Information Technology Agency, Blata l-Bajda, Malta {keith.cortis, judie.attard}@gov.mt Donatienne Spiteri Office of the State Advocate, Valletta, Malta donatienne.spiteri@stateadvocate.mt Abstract The work in progress on the CEF action National Language Technology Platform is presented. The action aims at combining the most advanced language technology tools and solutions in a new state-of-the-art, artificial-intelligence- driven, national platform for language technology oriented primarily towards users from public administrations of partner states. 1 Introduction The paper©presents the work in progress on the CEF action National Language Technology Platform (NLTP, INEA/CEF/ICT/A2020/ 2278398, duration 2021-04-01–2023-03-31). The © 2022 The authors. This article is licensed under a Creative Commons 3.0 licence, no derivative works, attribution, CC- BY-ND. general aim of the action is to combine the most advanced Language Technology (LT) tools and solutions in a new state-of-the-art, artificial- intelligence-driven, web-based national platform for LT. Currently, the action is approaching the implementation phase of the prototype systems. The system architecture plan has been created and will be followed by multiple implement- ations. In parallel, data collection and preparations for machine translation (MT) system training is gradually approaching its late stage. The details are described in section 2. 2 Development 2.1 Related work The developed solution builds on the already existing hugo.lv platform and the results of the EU Council Presidency Translator (INEA/CEF/ ICT/A2018/1762093) action, but it will be substantially extended into NLTP in order to provide public administrations and the general public with secure access to high quality MT and integration with computer aided translation (CAT) tools, e-mail and web plug-ins etc., for translation of texts and documents. This set of services is considered as initial, but the modular design of the platform allows it to be enriched with additional LT services beyond the initial set. 2.2 Users In its final form NLTP will be adapted, localised, and sustainably deployed by the public administration bodies in partner states (Latvia, Croatia, Estonia, Iceland, and Malta), while its development is supported at the same time by local research institutions as complementary partners. In the case of Iceland and Estonia, the research partners were given the role of public authorities as well. Additionally, the NLTP will be customisable to the specific needs of public administrations and will be further linked to eTranslation* services, thus enabling translations into and from the 24 official EU languages and other languages of the Digital Single Market. The NLTP will facilitate the use of a professional translation environment with integrated terminology databases, CAT and MT tools, all wrapped up in a simple-to-use …

Content truncated to 500 words