Roberta Tagalog Large

🚀 RoBERTa Tagalog Large

This Tagalog RoBERTa model is an improvement over our previous Tagalog pretrained Transformers. It is trained with TLUnified, a newer, larger, and more topically - varied pretraining corpus for Filipino. It's part of a larger research project, and we open - source it for wider use in the Filipino NLP community.

🚀 Quick Start

This section will be updated with quick - start instructions in the future.

✨ Features

• Improved Model: An enhanced version of previous Tagalog pretrained Transformers.
• New Corpus: Trained with TLUnified, a more comprehensive pretraining corpus for Filipino.
• Cased Model: This is a cased RoBERTa model, and uncased models are not released.

📚 Documentation

Citations

All model details and training setups can be found in our papers. If you use our model or find it useful in your projects, please cite our work:

@article{cruz2021improving,
  title={Improving Large - scale Language Models and Resources for Filipino},
  author={Jan Christian Blaise Cruz and Charibeth Cheng},
  journal={arXiv preprint arXiv:2111.06053},
  year={2021}
}

Data and Other Resources

Data used to train this model as well as other benchmark datasets in Filipino can be found on my website at https://blaisecruz.com

📄 License

This model is licensed under the CC - BY - SA 4.0 license.

📞 Contact

If you have questions, concerns, or if you just want to chat about NLP and low - resource languages in general, you may reach me through my work email at me@blaisecruz.com