PuoBERTa

PuoBerta: A curated Setswana Language Model

🤗 https://huggingface.co/dsfsi/PuoBERTa

Give Feedback 📑: DSFSI Resource Feedback Form

A Roberta-based language model specially designed for Setswana, using the new PuoData dataset.

Model Details

Model Description

This is a masked language model trained on Setswana corpora, making it a valuable tool for a range of downstream applications from translation to content creation. It's powered by the PuoData dataset to ensure accuracy and cultural relevance.

• Developed by: Vukosi Marivate (@vukosi), Moseli Mots'Oehli (@MoseliMotsoehli) , Valencia Wagner, Richard Lastrucci and Isheanesu Dzingirai
• Model type: RoBERTa Model
• Language(s) (NLP): Setswana
• License: CC BY 4.0

Usage

Use this model filling in masks or finetune for downstream tasks. Here’s a simple example for masked prediction:

from transformers import RobertaTokenizer, RobertaModel

# Load model and tokenizer
model = RobertaModel.from_pretrained('dsfsi/PuoBERTa')
tokenizer = RobertaTokenizer.from_pretrained('dsfsi/PuoBERTa')

Downstream Use

Downstream Performance

Daily News Dikgang

Learn more about the dataset in the Dataset Folder

Downstream News Categorisation model 🤗 https://huggingface.co/dsfsi/PuoBERTa-News

MasakhaPOS

Performance of models on the MasakhaPOS downstream task.

Downstream POS model 🤗 https://huggingface.co/dsfsi/PuoBERTa-POS

MasakhaNER

Performance of models on the MasakhaNER downstream task.

Downstream NER model 🤗 https://huggingface.co/dsfsi/PuoBERTa-NER

Pre-Training Dataset

We used the PuoData dataset, a rich source of Setswana text, ensuring that our model is well-trained and culturally attuned.

Github, 🤗 https://huggingface.co/datasets/dsfsi/PuoData

Citation Information

Bibtex Reference

@inproceedings{marivate2023puoberta,
  title   = {PuoBERTa: Training and evaluation of a curated language model for Setswana},
  author  = {Vukosi Marivate and Moseli Mots'Oehli and Valencia Wagner and Richard Lastrucci and Isheanesu Dzingirai},
  year    = {2023},
  booktitle= {Artificial Intelligence Research. SACAIR 2023. Communications in Computer and Information Science},
  url= {https://link.springer.com/chapter/10.1007/978-3-031-49002-6_17},
  keywords = {NLP},
  preprint_url = {https://arxiv.org/abs/2310.09141},
  dataset_url = {https://github.com/dsfsi/PuoBERTa},
  software_url = {https://huggingface.co/dsfsi/PuoBERTa}
}

Contributing

Your contributions are welcome! Feel free to improve the model.

Model Card Authors

Vukosi Marivate

Model Card Contact

For more details, reach out or check our website.

Email: vukosi.marivate@cs.up.ac.za

Enjoy exploring Setswana through AI!