# AraT5-base
# AraT5: Text-to-Text Transformers for Arabic Language Generation

<img src="AraT5_CR_new.png" alt="AraT5" width="55%" height="45%" align="right"/>

This is the repository accompanying our paper [AraT5: Text-to-Text Transformers for Arabic Language Understanding and Generation](https://arxiv.org/abs/2109.12068). In this is the repository we introduce:
* Introduce **AraT5<sub>MSA</sub>**, **AraT5<sub>Tweet</sub>**, and **AraT5**: three powerful Arabic-specific text-to-text Transformer based models;
* Introduce **ARGEN**:  A new benchmark for Arabic language generation and evaluation for four Arabic NLP tasks, namely, ```machine  translation```,  ```summarization```,  ```news title   generation```,   ```question   generation```, ,   ```paraphrasing```,   ```transliteration```, and  ```code-switched translation```.
* Evaluate  ```AraT5``` models on ```ARGEN``` and compare against available language models.

Our models establish new state-of-the-art (SOTA) on  several publicly available datasets.
Our language models are publicaly available for research (see below).

The rest of this repository provides more information about our new language models, benchmark, and experiments.

---
# How to use AraT5 models
Below is an example for fine-tuning **AraT5-base** for News Title Generation on the Aranews dataset 
``` bash
!python run_trainier_seq2seq_huggingface.py \
        --learning_rate 5e-5 \
        --max_target_length 128 --max_source_length 128 \
        --per_device_train_batch_size 8 --per_device_eval_batch_size 8 \
        --model_name_or_path "UBC-NLP/AraT5-base" \
        --output_dir "/content/AraT5_FT_title_generation" --overwrite_output_dir \
        --num_train_epochs 3 \
        --train_file "/content/ARGEn_title_genration_sample_train.tsv" \
        --validation_file "/content/ARGEn_title_genration_sample_valid.tsv" \
        --task "title_generation" --text_column "document" --summary_column "title" \
        --load_best_model_at_end --metric_for_best_model "eval_bleu" --greater_is_better True --evaluation_strategy epoch --logging_strategy epoch --predict_with_generate\
        --do_train --do_eval
```
For more details about the fine-tuning example, please read this notebook [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://github.com/UBC-NLP/araT5/blob/main/examples/Fine_tuning_AraT5.ipynb) 

In addition, we release the fine-tuned checkpoint of the News Title Generation (NGT) which is described in the paper. The model available at Huggingface ([UBC-NLP/AraT5-base-title-generation](https://huggingface.co/UBC-NLP/AraT5-base-title-generation)).

For more details, please visit our own [GitHub](https://github.com/UBC-NLP/araT5).





# AraT5 Models Checkpoints 

AraT5 Pytorch and TensorFlow checkpoints are available on the Huggingface website for direct download and use ```exclusively for research```. ```For commercial use, please contact the authors via email @ (muhammad.mageed[at]ubc[dot]ca).```

| **Model**   | **Link** | 
|---------|:------------------:|
|  **AraT5-base** |     [https://huggingface.co/UBC-NLP/AraT5-base](https://huggingface.co/UBC-NLP/AraT5-base)       | 
| **AraT5-msa-base**  |     [https://huggingface.co/UBC-NLP/AraT5-msa-base](https://huggingface.co/UBC-NLP/AraT5-msa-base)     |     
| **AraT5-tweet-base**  |   [https://huggingface.co/UBC-NLP/AraT5-tweet-base](https://huggingface.co/UBC-NLP/AraT5-tweet-base)    |      
| **AraT5-msa-small** |     [https://huggingface.co/UBC-NLP/AraT5-msa-small](https://huggingface.co/UBC-NLP/AraT5-msa-small)   |     
| **AraT5-tweet-small**|    [https://huggingface.co/UBC-NLP/AraT5-tweet-small](https://huggingface.co/UBC-NLP/AraT5-tweet-small) |  

# BibTex

If you use our models (Arat5-base, Arat5-msa-base, Arat5-tweet-base, Arat5-msa-small, or Arat5-tweet-small ) for your scientific publication, or if you find the resources in this repository useful, please cite our paper as follows (to be updated):
```bibtex
@inproceedings{araT5-2021,
    title = "{AraT5: Text-to-Text Transformers for Arabic Language Understanding and Generation",
    author = "Nagoudi, El Moatez Billah  and
      Elmadany, AbdelRahim  and
      Abdul-Mageed, Muhammad",
    booktitle = "https://arxiv.org/abs/2109.12068",
    month = aug,
    year = "2021"}
```

## Acknowledgments
We gratefully acknowledge support from the Natural Sciences and Engineering Research Council  of Canada, the  Social  Sciences and  Humanities  Research  Council  of  Canada, Canadian  Foundation for  Innovation,  [ComputeCanada](www.computecanada.ca) and [UBC ARC-Sockeye](https://doi.org/10.14288/SOCKEYE). We  also  thank  the  [Google TensorFlow Research Cloud (TFRC)](https://www.tensorflow.org/tfrc) program for providing us with free TPU access.