The **AraRoBERTa** models are mono-dialectal Arabic models trained on a country-level dialect. AraRoBERTa uses RoBERTa base config. More details are available in the paper [click](https://aclanthology.org/2022.wanlp-1.24/).

The following are the AraRoBERTa seven dialectal variations:

* [AraRoBERTa-SA](https://huggingface.co/reemalyami/AraRoBERTa-SA): Saudi Arabia (SA) dialect.
* [AraRoBERTa-EGY](https://huggingface.co/reemalyami/AraRoBERTa-EGY): Egypt (EGY) dialect.
* [AraRoBERTa-KU](https://huggingface.co/reemalyami/AraRoBERTa-KU): Kuwait (KU) dialect.
* [AraRoBERTa-OM](https://huggingface.co/reemalyami/AraRoBERTa-OM): Oman (OM) dialect.
* [AraRoBERTa-LB](https://huggingface.co/reemalyami/AraRoBERTa-LB): Lebanon (LB) dialect.
* [AraRoBERTa-JO](https://huggingface.co/reemalyami/AraRoBERTa-JO): Jordan (JO) dialect.
* [AraRoBERTa-DZ](https://huggingface.co/reemalyami/AraRoBERTa-DZ): Algeria (DZ) dialect

# When using the model, please cite our paper:

```python
@inproceedings{alyami-al-zaidy-2022-weakly,
    title = "Weakly and Semi-Supervised Learning for {A}rabic Text Classification using Monodialectal Language Models",
    author = "AlYami, Reem  and Al-Zaidy, Rabah",
    booktitle = "Proceedings of the The Seventh Arabic Natural Language Processing Workshop (WANLP)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.wanlp-1.24",
    pages = "260--272",
}
```

# Contact
**Reem AlYami**: [Linkedin](https://www.linkedin.com/in/reem-alyami/) | <reem.yami@kfupm.edu.sa> | <yami.m.reem@gmail.com>