@incollection{Kosem2022, author = {Iztok Kosem}, title = {Trendi - a monitor corpus of Slovene}, series = {Dictionaries and Society. Proceedings of the XX EURALEX International Congress, 12-16 July 2022, Mannheim, Germany}, editor = {Annette Klosa-K{\"u}ckelhaus and Stefan Engelberg and Christine M{\"o}hrs and Petra Storjohann}, publisher = {IDS-Verlag}, address = {Mannheim}, isbn = {978-3-937241-87-6}, doi = {10.14618/ids-pub-11180}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-111808}, pages = {230 -- 239}, year = {2022}, abstract = {In this paper we present Trendi, a monitor corpus of written Slovene, which has been compiled recently as part of the SLED (Monitor corpus and related resources) project. The methodology and the contents of the corpus are presented, as well as the findings of the survey that aimed to identify the needs of potential users related to topical language use. The Trendi corpus currently contains news articles and other web content from 110 different sources, with the texts being collected and linguistically annotated on a daily basis. The corpus complements Gigafida 2.0, a 1.13-billion-word reference corpus of standard written Slovene. Also discussed are the ways in which the corpus will be integrated into various lexicographic projects, helping not only in the identification of neologisms but also in monitoring changes in already identified language phenomena.}, language = {en} }