
Tuomas Salo
@tuomassalo
Tweeted On: March 28, 2020, 8:27 a.m.
Tuomas Salo
@tuomassalo
Tweeted On: March 28, 2020, 8:27 a.m.
Tweet this Thread as Reply
Share: Let others read this complete thread by @tuomassalo
The compound words are from analyzing all text from Finnish Wikipedia with Voikko (morphological analyzer). Most of the code is here: https://t.co/KPuKmCGpng
tuomassalo/wikipedia-voikko-analyzer
https://github.com/tuomassalo/wikipedia-voikko-analyzer
Tools to extract text from Finnish Wikipedia and feed it to Voikko. - tuomassalo/wikipedia-voikko-analyzer