| Abstract |
In this paper we show several segments of program solutions which are a part of the Croatian linguistic system (CLS) that is being developed in several ways and aims at achieving the final integration of all modules. Although the system aims at programmatically connecting all areas of linguistics (from phonetics to discourse), in the demonstration we will show only the segments that are related to general lexicon building (which includes a standard and terminological dictionary of the Croatian language) and will be connected with online repositories and encyclopedias. These program segments are searching for neologisms in documents (i.e. words that have not been marked in the general lexicon), generating grammatical forms of such words if they are changeable and saving them into a lexicon, adding semantic markups (like morphosyntactic) characteristics, and, finally, monitoring Croatian words in space and time. |
| BibTex |
@InProceedings{ELX2016-028,
author={Marko Orešković, Jakov Topić, Mario Essert},
title={Croatian Linguistic System Modules Overview},
pages={280-283},
booktitle={Proceedings of the 17th EURALEX International Congress},
year={2016},
month={sep},
date={6-10},
address={Tbilisi, Georgia},
editor={Tinatin Margalitadze, George Meladze},
publisher={Ivane Javakhishvili Tbilisi University Press},
isbn={978-9941-13-542-2},
} |
