Open morphology of Finnish

Read full text
Authors: Flammie A Pirinen
Cited by: 0

Abstract

New version has been packaged: Significant changes in 0.9.12 Updated nykysuomen sanalista to 2024 Updated wiktionaries to 2025-07 new paradigms for: kuudan noun, köyryselkä adj, tuppisuu adj, harmaahapsi adj, taxfree adj, kuullen, adp, taxfree adj, 4850 new lexemes: many prefixes and suffixes, compounds, e.g väliaikaisravintola (popup restaurant), trifle, tiedostomuoto (file format), tarvepainate (print on demand), abassi, apsi (mobile app) ... removed technical doublets of some numerals Swapped python library from HFST to pyhfst fixes to disambiguation based on data and experiments even more documentation about ambiguity started making a gold annotated disambiguation corpus by hand fixed a bug in fall-back (python based) tokenisation huge thanks to Patreons and Github Spongsors for their support

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
5 January 2026