Gn Bert Small Cased

🚀 BERT-i-small-cased (gnBERT-small-cased)

A pre-trained BERT model for Guarani (6 layers, cased), trained on Wikipedia + Wiktionary (~800K tokens).

🚀 Quick Start

This is a pre - trained BERT model specifically designed for the Guarani language. It has 6 layers and supports cased text. The model was trained on a combined dataset of Wikipedia and Wiktionary, which contains approximately 800K tokens.

📦 Installation

No installation steps were provided in the original document, so this section is skipped.

💻 Usage Examples

No code examples were provided in the original document, so this section is skipped.

📚 Documentation

Datasets

The model was trained on the following datasets:

• Wikipedia
• Wiktionary

Widget Examples

• 'Paraguay ha''e peteĩ táva oĩva [MASK] retãme '
• 'Augusto Roa Bastos ha'e peteĩ [MASK] arandu'

Metrics

The following metrics are used to evaluate the model:

• F1
• Accuracy

📄 License

This project is licensed under the MIT license.

📚 How to 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}
}