Article list
The latest version of the corpus of historical Slovak hist-7.0 contains 981,000 tokens. Is is made up of texts from the pre-codification period. It is comprised of both own project’s transliterated texts, as well as printed texts. The texts are not lemmatized nor morphologically annotated, users can search for a word form or use CQL….
Let us invite you to the workshop Corpus Databases – Data Sources Used in Research in Social Communication, that will take place on 21 January, 2024 at 2PM at the premises of the Institute for Research in Social Communication. Dr. Jana Levická from the Slovak National Corpus Department of Ľ. Štúr Institute of Linguistics SAS is going to present…
Did you know that the most frequent loanword used in Slovak is musieť (must)? Do you think that Slovak is endangered by English loanwords? Have you heard that artificial intelligence (AI) may have an influence on language? If you are interested in answers to these questions and you want to know more about automatic translators…
Listen to our colleague Radovan Garabík – a leading expert in natural language processing, language models and corpus linguistics, appearing tonight in the show Nočná pyramída on Rádio Slovensko. You can also listen to the show on the website https://slovensko.rtvs.sk/.