README.md

---
library_name: transformers
tags:
- readability
license: mit
base_model:
- aubmindlab/bert-base-arabertv2
pipeline_tag: text-classification
---

# AraBERTv2+D3Tok+CE Readability Model

## Model description
**AraBERTv2+D3Tok+CE** is a readability assessment model that was built by fine-tuning the **AraBERTv2** model with cross-entropy loss (**CE**).
For the fine-tuning, we used the **D3Tok** input variant from [BAREC-Corpus-v1.0](https://huggingface.co/datasets/CAMeL-Lab/BAREC-Corpus-v1.0).
Our fine-tuning procedure and the hyperparameters we used can be found in our paper *"[A Large and Balanced Corpus for Fine-grained Arabic Readability Assessment](https://arxiv.org/abs/2502.13520)."*

## Intended uses
You can use the AraBERTv2+D3Tok+CE model as part of the transformers pipeline.
You need to preprocess your text into the D3Tok input variant using the preprocessing step [here](https://github.com/CAMeL-Lab/barec_analyzer/tree/main).

## How to use
To use the model:

```python
from transformers import pipeline
readability = pipeline("text-classification", model="CAMeL-Lab/readability-arabertv2-d3tok-CE")
with open("/PATH/TO/preprocessed_d3tok", "r") as f:
    sentences = f.read().split("\n")
readability_levels = [int(readability(sentences)[i]['label'][6:])+1 for i in range(len(sentences))]
```

## Citation
```bibtex
@inproceedings{elmadani-etal-2025-readability,
    title = "A Large and Balanced Corpus for Fine-grained Arabic Readability Assessment",
    author = "Elmadani, Khalid N.  and
      Habash, Nizar  and
      Taha-Thomure, Hanada",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics"
}
```