Standalone contain extraction tools for Natural Language Processing (NLP) in IKT group
- Character Gazetteer
- Token Gazetteer
The work is an extention of ExPoS design based on Linear Substring Analysis (LSA)
- G. Nguyen, S. Dlugolinsky, M. Laclavík, M. Šeleng, V. Tran. Next improvement towards linear named entity recognition using character gazetteers. In Advances in Intelligent Systems and Computing : Advanced Computational Methods for Knowledge Engineering, 2014, vol. 282, p. 255-265. ISBN 978-3-319-06569-4. ISSN 2194-5357.
- S. Dlugolinsky, G. Nguyen, M. Laclavík, M. Šeleng. Character gazetteer for named entity recognition with linear matching complexity. In Proceedings of the 2013 World Congress on Information and Communication Technologies : WICT 2013. - IEEE Systems Man and Cybernetics Society, 2013, p. 364-368. ISBN 978-1-4799-3230-6.
- G. Nguyen, S. Dlugolinsky, M. Laclavík, M. Šeleng. Token Gazetteer and Character Gazetteer for Named Entity Recognition. In 8th Workshop on Intelligent and Knowledge Oriented Technologies : WIKT 2013, Košice, 2013, p. 1-6. ISBN 978-80-8143-128-9. Best paper award.
Authors: G. Nguyen, S. Dlugolinsky, M. Laclavik, M. Šeleng (2013-2014)