Extended semantic lexicon for FiST

This is an extended semantic lexicon for the updated Finnish semantic tagger FiST. The basic semantic lexicon of Finnish has been extended with lexemes from the vocabulary of modern Finnish available at Institute for the Languages of Finland. The original semantic lexicon of Finnish contains 46 226 lexical descriptions. The extended lexicon contains 96 306 lexemes. Part of the additions have been automatically marked with semantic tags. They look like this: #aakkosnimi#Noun#Q2.2 A11.1+/S2#NEW(from:nimi) --> semantic tag has been added along the base part of the compound nimi. Added semantic descriptions have not been checked in any way. If no semantic tag has been attached to an added lexeme, it is marked with only part-of-speech tag as #aakkosellisuus#Noun##NEW References Kimmo Kettunen. 2019. FiST – towards a free Semantic Tagger of modern standard Finnish. In Proceedings of the Fifth International Workshop on Computational Linguistics for Uralic Languages, pages 66–76, Tartu, Estonia. Association for Computational Linguistics. Nykysuomen sanalista. Kotimaisten kielten keskus. Updated 30.4.2024 [referred 20.03.2026]. Available at https://kaino.kotus.fi/lataa/nykysuomensanalista2024.txt UCREL/Multilingual-USAS Available at https://github.com/UCREL/Multilingual-USAS/tree/master/Finnish