stanfordnlp
Support Swahili
Is Swahili a language you're working on?
Based on the requests for other languages, it sounds like the first step is to create a Universal Dependencies description.
Kenneth Steimel (@ksteimel) is working on Swahili (see this presentation) but I don't know what the status is. Are you working with him?
I noticed that https://github.com/UniversalDependencies/UD_Swahili-OPUSGV/blob/dev/README.md says 2021-05-15. I'm not sure if that's a typo or the projected release date of the corpus.
It's good to hear that there's additional interest in Swahili NLP!
I am working on a treebank as one part of my PhD thesis. The projected release date is may of next year because that was my target for completing my thesis. However, things have come up so it may be delayed a month or two.
I'll work to keep the repo more up to date so you can see my progress more clearly. Sorry about that.
@tbm very likely that that date is a projected release date for UD v2.8. We will definitely consider training a Swahili model should the data become available as part of UD!
