microbert-wolof-mxp / README.md
lgessler's picture
Create README.md
49648cb
metadata
language: wol
widget:
  - text: Looloo taxoon ñuy réew yu naat.

This is a MicroBERT model for Wolof.

  • Its suffix is -mxp, which means that it was pretrained using supervision from masked language modeling, XPOS tagging, and UD dependency parsing.
  • The unlabeled Wolof data was taken from a February 2022 dump of Uyghur Wikipedia, totaling 517,237 tokens.
  • The UD treebank UD_Wolof-WDT, v2.9, totaling 44,258 tokens, was used for labeled data.

Please see the repository and the paper for more details.