filevich's picture
Update README.md
808ec37 verified
metadata
language:
  - es
tags:
  - masked-lm
  - roberta
license: mit
datasets:
  - filevich/uy22

ROUBERTa cased

This is a RoBERTa-base LM trained from scratch exclusively on Uruguayan press [1].

Cite this work

@inproceedings{rouberta2024,
  title={A Language Model Trained on Uruguayan Spanish News Text},
  author={Filevich, Juan Pablo and Marco, Gonzalo and Castro, Santiago and Chiruzzo, Luis and Ros{\'a}, Aiala},
  booktitle={Proceedings of the Second International Workshop Towards Digital Language Equality (TDLE): Focusing on Sustainability@ LREC-COLING 2024},
  pages={53--60},
  year={2024}
}

[1] huggingface.co/datasets/pln-udelar/uy22