Skip to main content

5.1.24. Slovenia

FLaReNet Summary

Several research institutions and companies in Slovenia are working in the field of language technologies. On the development of written language resources for the Slovenian language: Institute Jozef Stefan (Department of knowledge technologies), University of Ljubljana (Faculty of Art, Department of Translation Studies), Amebis d.o.o., the University of Ljubljana (Faculty of Electrical Engineering), the University of Maribor (Faculty of Electrical Engineering and Computer Science). On the development of spoken language resources: University of Ljubljana (Faculty of Electrical Engineering), University of Maribor (Faculty of Electrical Engineering and Computer Science), Alpineon d.o.o. There exist a Slovenian Language Technologies Society.

FIDA Plus is presently the largest text corpus of Slovenian language. A project on the development of a national speech corpus is currently under way.

Contact Point Input

National/Regional contact: Marko Grobelnik, Jožef Stefan Institute.
National/Regional contact: Zdravko Kacik, University of Maribor.

Programs

Several research institutions and companies in Slovenia are working in the field of language technologies.

The following institutions are working on development of written language resources for Slovenian language and NLP:

  - Institute Jozef Stefan, Department of knowledge technologies

(Web: http://kt.ijs.si, Contact person: Dr. Tomaž Erjavec, Email: tomaz.erjavec@ijs.si)

XML description of available language resources at IJS:
http://nl2.ijs.si/oai/oai.pl?verb=ListRecords&metadataPrefix=oai_clarin.

Two pointers on Slovenian Language resources - in the next months there will be one slightly more consolidated page:
http://kt.ijs.si/dunja/TextWebJSI/ - computational linguistics;
http://nl.ijs.si - corpus linguistics.

  - Faculty of Art, University of Ljubljana, Department of Translation Studies

(Web: http://lojze.lugos.si/~spela/, Contact person: Špela Vintar, Email: spela.vintar@ff.uni-lj.si)

  - Amebis, d.o.o.

(Web: http://www.amebis.si, Contact person: Miro Romih, Email: miro.romih@amebis.si)

  - University of Ljubljana, Faculty of Electrical Engineering

(Web: http://luks.fe.uni-lj.si, Contact: Prof. dr. France Mihelič, Email: france.mihelic@fe.uni-lj.si)

  - University of Maribor, Faculty of Electrical Engineering and Computer Science

(Web: http://www.dsplab.uni-mb.si/Dsplab/index_eng.php, Contact: Dr. Darinka Verdonik, E-mail: darinka.verdonik@uni-mb.si)

The following institutions are working on development of spoken language resources for Slovenian language and speech technology:

  - University of Ljubljana, Faculty of Electrical Engineering

(Web: http://luks.fe.uni-lj.si, Contact: Prof. Dr. France Mihelič, Email: france.mihelic@fe.uni-lj.si)

  - University of Maribor, Faculty of Electrical Engineering and Computer Science

(Web: http://www.dsplab.uni-mb.si/Dsplab/index_eng.php, Contact: Prof. Dr. Zdravko Kačič, Email: kacic@uni-mb.si)

  - Alpineon d.o.o.

(Web: http://www.alpineon.com, Contact: Dr. Jerneja Gros, Email: jerneja.gros@alpineon.com)

Web page of The Slovenian Language Technologies Society:
http://www.sdjt.si/index-en.html;
http://www.sdjt.si/sdjt-www-en.html - description of several language resources.

A project of development of national speech corpus is currently under way and the corpus web page www.korpus-gos.net will soon be available.

The web page of the largest text corpus of Slovenian language FIDA Plus is:

http://www.fidaplus.net/Index_eng.htm.

Slovenia is participating in the preparation of a COST Action proposal regarding the development and evaluation of speech based multimodal output interfaces, with the main idea to bring up a web based infrastructure for evaluation of speech technology modules and systems (speech synthesis), which will provide possibilities to perform evaluation campaigns of modules and complete systems throughout the Europe. The present consortium consists of 21 partners from 14 different European countries and China, covering 16 different languages.