|
|
--- |
|
|
base_model: |
|
|
- dbmdz/bert-base-turkish-uncased |
|
|
language: |
|
|
- tr |
|
|
library_name: transformers |
|
|
license: cc-by-4.0 |
|
|
pipeline_tag: text-classification |
|
|
--- |
|
|
# Model Card for AntiMisogynyTurk |
|
|
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
|
|
This model is created by fine-tuning the famous BERTurk model that was already pretrained to work |
|
|
on Turkish language. Here, it is fine-tuned to detect hate and prejudice against women from Turkish texts. |
|
|
|
|
|
The model is fine-tuned using social media posts. |
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
|
|
|
|
|
|
|
|
- **Developed by:** Dr. Ulya BAYRAM |
|
|
- **Model type:** Classification |
|
|
- **License:** Creative Commons |
|
|
- **Finetuned from model:** BERTurk |
|
|
|
|
|
## How to Get Started with the Model |
|
|
|
|
|
Use the code below to get started with the model. |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
|
|
|
## Training Data |
|
|
|
|
|
To train this model, a private data collection scraped from social media, and then manually labeled by experts is used. |
|
|
|
|
|
The dataset is available to researchers per demand with the conditions of using it only for research purposes and not sharing it with others. |
|
|
|
|
|
|
|
|
## Model Source and Citation |
|
|
|
|
|
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> |
|
|
|
|
|
When using this model for your research, please cite the following paper, which is the source of the model: |
|
|
|
|
|
**Paper:** Paper submitted, coming soon |
|
|
|
|
|
**BibTeX:** |
|
|
|
|
|
Paper submitted, coming soon |
|
|
|
|
|
**APA:** |
|
|
|
|
|
Paper submitted, coming soon |
