Update README.md
Browse files
README.md
CHANGED
@@ -9,6 +9,10 @@ license: gpl-3.0
|
|
9 |
inference: false
|
10 |
---
|
11 |
|
|
|
|
|
|
|
|
|
12 |
# DistilBERT Tagalog Base Cased
|
13 |
Tagalog version of DistilBERT, distilled from [`bert-tagalog-base-cased`](https://huggingface.co/jcblaise/bert-tagalog-base-cased). This model is part of a larger research project. We open-source the model to allow greater usage within the Filipino NLP community.
|
14 |
|
@@ -32,15 +36,6 @@ Finetuning scripts and other utilities we use for our projects can be found in o
|
|
32 |
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:
|
33 |
|
34 |
```
|
35 |
-
@inproceedings{localization2020cruz,
|
36 |
-
title={{Localization of Fake News Detection via Multitask Transfer Learning}},
|
37 |
-
author={Cruz, Jan Christian Blaise and Tan, Julianne Agatha and Cheng, Charibeth},
|
38 |
-
booktitle={Proceedings of The 12th Language Resources and Evaluation Conference},
|
39 |
-
pages={2589--2597},
|
40 |
-
year={2020},
|
41 |
-
url={https://www.aclweb.org/anthology/2020.lrec-1.315}
|
42 |
-
}
|
43 |
-
|
44 |
@article{cruz2020establishing,
|
45 |
title={Establishing Baselines for Text Classification in Low-Resource Languages},
|
46 |
author={Cruz, Jan Christian Blaise and Cheng, Charibeth},
|
@@ -60,4 +55,4 @@ All model details and training setups can be found in our papers. If you use our
|
|
60 |
Data used to train this model as well as other benchmark datasets in Filipino can be found in my website at https://blaisecruz.com
|
61 |
|
62 |
## Contact
|
63 |
-
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
|
|
|
9 |
inference: false
|
10 |
---
|
11 |
|
12 |
+
**Deprecation Notice**
|
13 |
+
This model is deprecated. New Filipino Transformer models trained with a much larger corpora are available.
|
14 |
+
Use [`jcblaise/roberta-tagalog-base`](https://huggingface.co/jcblaise/roberta-tagalog-base) or [`jcblaise/roberta-tagalog-large`](https://huggingface.co/jcblaise/roberta-tagalog-large) instead for better performance.
|
15 |
+
|
16 |
# DistilBERT Tagalog Base Cased
|
17 |
Tagalog version of DistilBERT, distilled from [`bert-tagalog-base-cased`](https://huggingface.co/jcblaise/bert-tagalog-base-cased). This model is part of a larger research project. We open-source the model to allow greater usage within the Filipino NLP community.
|
18 |
|
|
|
36 |
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:
|
37 |
|
38 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
@article{cruz2020establishing,
|
40 |
title={Establishing Baselines for Text Classification in Low-Resource Languages},
|
41 |
author={Cruz, Jan Christian Blaise and Cheng, Charibeth},
|
|
|
55 |
Data used to train this model as well as other benchmark datasets in Filipino can be found in my website at https://blaisecruz.com
|
56 |
|
57 |
## Contact
|
58 |
+
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
|