bert-base-sw / README.md
GorkaUrbizu's picture
Update README.md
900a609
---
license: cc-by-4.0
language:
- sw
---
BERT base (cased) model trained on a subset of 125M tokens of cc100-Swahili for our work [Scaling Laws for BERT in Low-Resource Settings](https://aclanthology.org/2023.findings-acl.492.pdf) at ACL2023 Findings.
The model has 124M parameters (12L), and a vocab size of 50K.
It was trained for 500K steps with a sequence length of 512 tokens and batch-size of 256.
Results
-----------
| | [bert-base-sw](https://huggingface.co/orai-nlp/bert-base-sw) | [bert-medium-sw](https://huggingface.co/orai-nlp/bert-medium-sw) | Flair | [mBERT](https://huggingface.co/bert-base-multilingual-cased) | [SwahBERT](https://github.com/gatimartin/SwahBERT#pre-trained-models) |
|-----------|--------------|----------------|-------|-------|---------------------------------|
| NERC | **92.09** | 91.63 | 92.04 | 91.17 | 88.60 |
| Topic | **93.07** | 92.88 | 91.83 | 91.52 | 90.90 |
| Sentiment | **79.04** | 77.07 | 73.60 | 69.17 | 71.12 |
| QNLI | 63.34 | 63.87 | 52.82 | 63.48 | **64.72** |
Authors
-----------
Gorka Urbizu [1], Iñaki San Vicente [1], Xabier Saralegi [1],
Rodrigo Agerri [2] and Aitor Soroa [2]
Affiliation of the authors:
[1] Orai NLP Technologies
[2] HiTZ Center - Ixa, University of the Basque Country UPV/EHU
Licensing
-------------
The model is licensed under the Creative Commons Attribution 4.0. International License (CC BY 4.0).
To view a copy of this license, visit [http://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/deed.eu).
Acknowledgements
-------------------
If you use this model please cite the following paper:
- G. Urbizu, I. San Vicente, X. Saralegi, R. Agerri, A. Soroa. Scaling Laws for BERT in Low-Resource Settings. Findings of the Association for Computational Linguistics: ACL 2023. July, 2023. Toronto, Canada
Contact information
-----------------------
Gorka Urbizu, Iñaki San Vicente: {g.urbizu,i.sanvicente}@orai.eus