Language Technology at UiT

The Divvun and Giellatekno teams build language technology aimed at minority and indigenous languages

View GiellaLT on GitHub divvungiellatekno/giellalt.uit.no

Page Content

Proofing meeting

Last speller compiled some three weeks ago. Nothing new since then.

Thomas has lexicalised a number of compounds. Stil a lot to go. Thomas will prioritise the candidate words from the bound corpus from now on. Those are mostly Ávvir words.

Tomi will move vuohta derivations from regular derivation to compounding, just for the PLX conversion. Doing that will reduce the PLX file size from 60 Gb to 20, which seems to remove the strange and unpredictable behaviour we have seen in some cases.