Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: tl
|
| 3 |
+
tags:
|
| 4 |
+
- roberta
|
| 5 |
+
- tagalog
|
| 6 |
+
- filipino
|
| 7 |
+
license: cc-by-sa-4.0
|
| 8 |
+
inference: false
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# RoBERTa Tagalog Large
|
| 12 |
+
Tagalog RoBERTa trained as an improvement over our previous Tagalog pretrained Transformers. Trained with TLUnified, a newer, larger, more topically-varied pretraining corpus for Filipino. This model is part of a larger research project. We open-source the model to allow greater usage within the Filipino NLP community.
|
| 13 |
+
|
| 14 |
+
This model is a cased model. We do not release uncased RoBERTa models.
|
| 15 |
+
|
| 16 |
+
## Citations
|
| 17 |
+
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:
|
| 18 |
+
|
| 19 |
+
```
|
| 20 |
+
@article{cruz2021improving,
|
| 21 |
+
title={Improving Large-scale Language Models and Resources for Filipino},
|
| 22 |
+
author={Jan Christian Blaise Cruz and Charibeth Cheng},
|
| 23 |
+
journal={arXiv preprint arXiv:2111.06053},
|
| 24 |
+
year={2021}
|
| 25 |
+
}
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
## Data and Other Resources
|
| 29 |
+
Data used to train this model as well as other benchmark datasets in Filipino can be found in my website at https://blaisecruz.com
|
| 30 |
+
|
| 31 |
+
## Contact
|
| 32 |
+
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
|