SLOKIT

The SLOKIT project (Upgrading CLARIN.SI: Corpus Informer and Text Analyser) has produced two important linguistic resources, the corpus data summariser Korpusnik and the sentence simplification and analysis application Senta. The resources were developed by the team of the Jožef Štefan Institute in cooperation with the Association of Disabled Students and with the infrastructural support of the Centre for Language Resources and Technologies of the University of Ljubljana within the CLARIN.SI consortium.

The corpus provides a quick basic overview of word usage in five corpora – Gigafida 2.0, Trends 2023-09, OSS 1.0, JANES 1.0 and Gos 2.0. The user can thus check the usage of words in standard, trending, academic, online and spoken Slovene in one place. The Senta app is designed to simplify texts. It simplifies complex sentences and leaves simple sentences unchanged. It also produces an analysis with basic text statistics. Both resources are special in that they are also adapted for use by people with disabilities.