Added BibTex citations for models and dataset
Browse files
README.md
CHANGED
|
@@ -10,7 +10,38 @@ widget:
|
|
| 10 |
---
|
| 11 |
# bcms-bertic-frenk-hate
|
| 12 |
|
| 13 |
-
Text classification model based on `classla/bcms-bertic` and fine-tuned on the [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
## Fine-tuning hyperparameters
|
| 16 |
|
|
@@ -55,6 +86,8 @@ Comparison with `xlm-roberta-base`:
|
|
| 55 |
|Mann Whithney|0.00107|0.00108|
|
| 56 |
|Student t-test |4.83e-11 | 5.61e-11 |
|
| 57 |
|
|
|
|
|
|
|
| 58 |
## Use examples
|
| 59 |
|
| 60 |
```python
|
|
|
|
| 10 |
---
|
| 11 |
# bcms-bertic-frenk-hate
|
| 12 |
|
| 13 |
+
Text classification model based on [`classla/bcms-bertic`](https://huggingface.co/classla/bcms-bertic) and fine-tuned on the [FRENK dataset](https://www.clarin.si/repository/xmlui/handle/11356/1433) comprising of LGBT and migrant hatespeech. Only the Croatian subset of the data was used for fine-tuning and the dataset has been relabeled for binary classification (offensive or acceptable).
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
If you use the model, please cite the following paper on which the original model is based:
|
| 18 |
+
```
|
| 19 |
+
@inproceedings{ljubesic-lauc-2021-bertic,
|
| 20 |
+
title = "{BERT}i{\'c} - The Transformer Language Model for {B}osnian, {C}roatian, {M}ontenegrin and {S}erbian",
|
| 21 |
+
author = "Ljube{\v{s}}i{\'c}, Nikola and Lauc, Davor",
|
| 22 |
+
booktitle = "Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing",
|
| 23 |
+
month = apr,
|
| 24 |
+
year = "2021",
|
| 25 |
+
address = "Kiyv, Ukraine",
|
| 26 |
+
publisher = "Association for Computational Linguistics",
|
| 27 |
+
url = "https://www.aclweb.org/anthology/2021.bsnlp-1.5",
|
| 28 |
+
pages = "37--42",
|
| 29 |
+
}
|
| 30 |
+
```
|
| 31 |
+
|
| 32 |
+
and the dataset used for fine-tuning:
|
| 33 |
+
```
|
| 34 |
+
@misc{ljubešić2019frenk,
|
| 35 |
+
title={The FRENK Datasets of Socially Unacceptable Discourse in Slovene and English},
|
| 36 |
+
author={Nikola Ljubešić and Darja Fišer and Tomaž Erjavec},
|
| 37 |
+
year={2019},
|
| 38 |
+
eprint={1906.02045},
|
| 39 |
+
archivePrefix={arXiv},
|
| 40 |
+
primaryClass={cs.CL},
|
| 41 |
+
url={https://arxiv.org/abs/1906.02045}
|
| 42 |
+
}
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
|
| 46 |
## Fine-tuning hyperparameters
|
| 47 |
|
|
|
|
| 86 |
|Mann Whithney|0.00107|0.00108|
|
| 87 |
|Student t-test |4.83e-11 | 5.61e-11 |
|
| 88 |
|
| 89 |
+
|
| 90 |
+
|
| 91 |
## Use examples
|
| 92 |
|
| 93 |
```python
|