---
license: openrail++
datasets:
- ukr-detect/ukr-toxicity-dataset-seminatural
language:
- uk
widget:
- text: Ти неймовірна!
---

## Binary toxicity classifier for Ukrainian

This is the fine-tuned on the semi-automatically collected [Ukrainian toxicity classification dataset](https://huggingface.co/datasets/ukr-detect/ukr-toxicity-dataset) ["xlm-roberta-base"](https://huggingface.co/xlm-roberta-base) instance. 

The evaluation metrics for binary toxicity classification on a test set are: 

| Metric    | Value |
|-----------|-------|
| F1-score  | 0.99  |
| Precision | 0.99  |
| Recall    | 0.99  |
| Accuracy  | 0.99  |


## How to use: 

```
from transformers import pipeline

classifier = pipeline("text-classification",
                       model="ukr-detect/ukr-toxicity-classifier")
```

## Citation

```
@article{dementieva2024toxicity,
  title={Toxicity Classification in Ukrainian},
  author={Dementieva, Daryna and Khylenko, Valeriia and Babakov, Nikolay and Groh, Georg},
  journal={arXiv preprint arXiv:2404.17841},
  year={2024}
}
```