@inproceedings{3ff13dac4c684469bb48e65f0de88ae1,
title = "National Language Technology Platform for Public Administration",
abstract = "This article presents the work in progress on the collaborative project of several European countries to develop National Language Technology Platform (NLTP). The project aims at combining the most advanced Language Technology tools and solutions in a new, state-of-the-art, Artificial Intelligence driven, National Language Technology Platform for five EU/EEA official and lower-resourced languages.",
keywords = "CAT tools, National Language Technology Platform, machine translation, parallel corpora",
author = "Marko Tadi{\'c} and Da{\v s}a Farka{\v s} and Matea Filko and Artūrs Vasiļevskis and Andrejs Vasiļjevs and Jānis Ziediņ{\v s} and {\v Z}eljka Motika and Mark Fishel and Hrafn Loftsson and J{\'o}n Gu{\dh}nason and Claudia Borg and Keith Cortis and Judie Attard and Donatienne Spiteri",
note = "Funding Information: The work reported here was supported by the European Commission in the CEF Telecom Programme (Action No: 2020-EU-IA-0082, Grant Agreement No: INEA/CEF/ ICT/A2020/2278398). Funding Information: Technological support for Croatian has progressed in a number of LT areas compared to the state of affairs described in the META-NET White Paper (Tadi{\'c} et al., 2012). Digital language resources have both increased in number and volume while they also improved in quality and variety. Resources, basic NLP tools and LT services are provided by academia, research institutes and occasionally private companies as outputs of various research projects, usually coordinated by academic institutions, predominantly funded by EU or national funds, and rarely self-funded. Some significant progress has been made with respect to available corpora and lexica, language models, text processing tools, and MT, while there is still a serious underdevelopment in the field of speech processing (both synthesis and recognition). The available datasets originate from a variety of sources and they cover several thematic domains, text types; they are available as raw or annotated; and come as monolingual, bilingual or multilingual resources. However, their individual size is lagging behind in terms of appropriateness for building large language models or robust, ready to use tools and applications. Publisher Copyright: {\textcopyright} European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.; 2022 Towards Digital Language Equality Workshop, TDLE 2022 ; Conference date: 20-06-2022",
year = "2022",
language = "English",
series = "Towards Digital Language Equality Workshop, TDLE 2022 - as part of the International Conference on Language Resources and Evaluation, LREC 2022",
publisher = "European Language Resources Association (ELRA)",
pages = "46--51",
editor = "Itziar Aldabe and Begona Altuna and Aritz Farwell and German Rigau",
booktitle = "Towards Digital Language Equality Workshop, TDLE 2022 - as part of the International Conference on Language Resources and Evaluation, LREC 2022",
}