Views
No views yet
1!python run_trainier_seq2seq_huggingface.py \
2 --learning_rate 5e-5 \
3 --max_target_length 128 --max_source_length 128 \
4 --per_device_train_batch_size 8 --per_device_eval_batch_size 8 \
5 --model_name_or_path "UBC-NLP/AraT5-base" \
6 --output_dir "/content/AraT5_FT_title_generation" --overwrite_output_dir \
7 --num_train_epochs 3 \
8 --train_file "/content/ARGEn_title_genration_sample_train.tsv" \
9 --validation_file "/content/ARGEn_title_genration_sample_valid.tsv" \
10 --task "title_generation" --text_column "document" --summary_column "title" \
11 --load_best_model_at_end --metric_for_best_model "eval_bleu" --greater_is_better True --evaluation_strategy epoch --logging_strategy epoch --predict_with_generate\
12 --do_train --do_eval
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 |
| AraT5-msa-base | https://huggingface.co/UBC-NLP/AraT5-msa-base |
| AraT5-tweet-base | https://huggingface.co/UBC-NLP/AraT5-tweet-base |
| AraT5-msa-small | https://huggingface.co/UBC-NLP/AraT5-msa-small |
| AraT5-tweet-small | https://huggingface.co/UBC-NLP/AraT5-tweet-small |
1@inproceedings{nagoudi2022_arat5,
2@inproceedings{nagoudi-etal-2022-arat5,
3 title = "{A}ra{T}5: Text-to-Text Transformers for {A}rabic Language Generation",
4 author = "Nagoudi, El Moatez Billah and
5 Elmadany, AbdelRahim and
6 Abdul-Mageed, Muhammad",
7 booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
8 month = may,
9 year = "2022",
10 address = "Dublin, Ireland",
11 publisher = "Association for Computational Linguistics",
12 url = "https://aclanthology.org/2022.acl-long.47",
13 pages = "628--647",
14 abstract = "Transfer learning with a unified Transformer framework (T5) that converts all language problems into a text-to-text format was recently proposed as a simple and effective transfer learning approach. Although a multilingual version of the T5 model (mT5) was also introduced, it is not clear how well it can fare on non-English tasks involving diverse data. To investigate this question, we apply mT5 on a language with a wide variety of dialects{--}Arabic. For evaluation, we introduce a novel benchmark for ARabic language GENeration (ARGEN), covering seven important tasks. For model comparison, we pre-train three powerful Arabic T5-style models and evaluate them on ARGEN. Although pre-trained with {\textasciitilde}49 less data, our new models perform significantly better than mT5 on all ARGEN tasks (in 52 out of 59 test sets) and set several new SOTAs. Our models also establish new SOTA on the recently-proposed, large Arabic language understanding evaluation benchmark ARLUE (Abdul-Mageed et al., 2021). Our new models are publicly available. We also link to ARGEN datasets through our repository: https://github.com/UBC-NLP/araT5.",
15}1@inproceedings{elmadany-etal-2023-octopus,
2 title = "Octopus: A Multitask Model and Toolkit for {A}rabic Natural Language Generation",
3 author = "Elmadany, AbdelRahim and
4 Nagoudi, El Moatez Billah and
5 Abdul-Mageed, Muhammad",
6 booktitle = "Proceedings of ArabicNLP 2023",
7 month = dec,
8 year = "2023",
9 address = "Singapore (Hybrid)",
10 publisher = "Association for Computational Linguistics",
11 url = "https://aclanthology.org/2023.arabicnlp-1.20",
12 doi = "10.18653/v1/2023.arabicnlp-1.20",
13 pages = "232--243",
14}