Hugging Face's logo

sultan
/
ArabicT5-17GB-large

Text2Text Generation
Transformers
PyTorch
t5
text-generation-inference
Inference Endpoints
Model card Files Community
2
ArabicT5-17GB-large / README.md
sultan's picture
sultan
Update README.md
d3eaa97
preview code
|
raw
history blame
6.97 kB

ArabicT5: Efficient Adaptation of T5 on Arabic Language

Model Description

This model adapts T5 on the Arabic Language by pre-training T5 on :

  • Arabic Wikipedia.
  • Marefa encyclopedia.
  • Hindawi Books.
  • a collection of Arabic News.

Total Corpora size is 17GB. This model uses an efficient implementation of T5 which reduces the fine-tuning and memory used Link and uses T5x for pre-training Link

Pre-training Settings and Results on TyDi QA Development Dataset ( Model in this card is highlighted in bold )

Model Hidden Layer Atten. head Atten. Layers Vocab Hardware Training Steps Batch Train x Batch Factor Corpora
AraT5-base 768 12 12 110K TPUv3-8 1M 128 1.0x 248GB 29B tokens (MSA + Tweets)
AraT5-msa-base 768 12 12 110K TPUv3-8 1M 128 1.0x 70GB (MSA)
AraT5-tweets-base 768 12 12 110K TPUv3-8 1M 128 1.0x 178GB (Tweets)
AraBART-base 768 12 12 50K 128 V100 GPUs (60h) 25 epochs - - 73GB (MSA)
mT5-base 768 12 12 250K TPUv3-32 1M 1024 8.0x 6.3T tokens (mC4)
ArabicT5-17GB-small 512 8 20 32K TPUv3-32 256K 256 0.5x 17GB (MSA)
ArabicT5-49GB-small 512 8 16 32K TPUv3-64 500K 256 1.0x 49GB (MSA + OSCAR)
ArabicT5-17GB-base 768 12 16 32K TPUv3-128 500K 512 2.0x 17GB (MSA)
ArabicT5-49GB-base 768 12 16 32K TPUv3-64 500K 256 1.0x 49GB (MSA + OSCAR)
ArabicT5-17GB-large 768 12 36 32K TPUv3-128 500K 512 2.0x 17GB (MSA)

Results on TyDi QA, HARD, Sentiment Analysis, Sarcasm Detection ( Best Score is highlighted in bold )

Model
TyDi QA
HARD
ArSarcasm-v2-Sentiment
ArSarcasm-v2-Sarcasm
 XL-SUM
AraT5-base
70.4/84.2
96.5
69.7/72.6
60.4
30.3
AraT5-msa-base
70.9/84.0
96.5
70.0/72.7
60.7
27.4
AraT5-tweets-base
65.1/79.0
96.3
70.7/73.5
61.1
25.1
mT5-base
72.2/84.1
96.2
67.3/68.8
52.2
25.7
AraBART-base
48.8/71.2
96.1
66.2/68.2
56.3
31.2
ArabicT5-17GB-small
70.8/84.8
96.4
68.9/71.2
58.9
29.2
ArabicT5-49GB-small
72.4/85.1
96.4
70.2/73.4
61.0
30.2
ArabicT5-17GB-base
73.3/86.1
96.4
70.4/73.0
59.8
30.3
ArabicT5-49GB-base
72.1/85.1
96.5
71.3/74.1
60.4
30.9
ArabicT5-17GB-large
75.5/87.1
96.5
72.2/75.2
61.7
31.7

Evaluation Metrics: TyDi QA (EM/F1), HARD (Accuracy), Sentiment Analysis (Accuracy / F1-PN positive-negative), Sarcasm Detection (F1-sarcastic), XL-SUM (Rouge-L with Stemmer).

You can download the full details of our grid search for all models in all tasks above from this link: https://github.com/salrowili/ArabicT5/raw/main/ArabicT5_Grid_Search.zip

For the XL-Sum task, we choose our best run for each model using the eval set. We use the official evaluation script from XL-Sum, which uses the stemmer function, which may show better results than papers that don't use the stemmer function. The official XL-Sum paper uses a stemmer function.

Continual Pre-Training of ArabicT5 with T5x

if you want to continue pre-training ArabicT5 on your own data, we have uploaded the raw t5x checkpoint to this link https://huggingface.co/sultan/ArabicT5-49GB-base/blob/main/arabict5_49GB_base_t5x.tar.gz We will soon share a tutorial on how you can do that for free with Kaggle TPU

FineTuning our ArabicT5 model on generative and abstractive tasks with FLAX

Open In Colab

GitHub Page

https://github.com/salrowili/ArabicT5

Acknowledgment

We want to acknowledge the support we have from The TPU Research Cloud (TRC) team to grant us access to TPUv3 units.

Paper

Generative Approach for Gender-Rewriting Task with ArabicT5

Citation 

@inproceedings{alrowili-shanker-2022-generative,
    title = "Generative Approach for Gender-Rewriting Task with {A}rabic{T}5",
    author = "Alrowili, Sultan  and
      Shanker, Vijay",
    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-1.55",
    pages = "491--495",
    abstract = "Addressing the correct gender in generative tasks (e.g., Machine Translation) has been an overlooked issue in the Arabic NLP. However, the recent introduction of the Arabic Parallel Gender Corpus (APGC) dataset has established new baselines for the Arabic Gender Rewriting task. To address the Gender Rewriting task, we first pre-train our new Seq2Seq ArabicT5 model on a 17GB of Arabic Corpora. Then, we continue pre-training our ArabicT5 model on the APGC dataset using a newly proposed method. Our evaluation shows that our ArabicT5 model, when trained on the APGC dataset, achieved competitive results against existing state-of-the-art methods. In addition, our ArabicT5 model shows better results on the APGC dataset compared to other Arabic and multilingual T5 models.",
}