README.md

metadata

language: gn
license: mit
datasets:
  - wikipedia
  - wiktionary
widget:
  - text: Paraguay ha'e peteĩ táva oĩva [MASK] retãme
  - text: Augusto Roa Bastos ha'e peteĩ [MASK] arandu
metrics:
  - f1
  - accuracy

BERT-i-base-cased (gnBERT-base-cased)

A pre-trained BERT model for Guarani (12 layers, cased). Trained on Wikipedia + Wiktionary (~800K tokens).

How cite?

@article{aguero-et-al2023multi-affect-low-langs-grn,
  title={Multidimensional Affective Analysis for Low-resource Languages: A Use Case with Guarani-Spanish Code-switching Language},
  author={Agüero-Torales, Marvin Matías, López-Herrera, Antonio Gabriel, and Vilares, David},
  journal={Cognitive Computation},
  year={2023},
  publisher={Springer},
  notes={Forthcoming}
}