Update README.md

README.md

@@ -1,13 +1,50 @@
+---
+language: 
+  - ar
+tags:
+  - Arabic T5
+  - MSA
+  - Twitter
+  - Arabic Dialect
+  - Arabic Machine Translation
+  - Arabic Text Summarization
+  - Arabic News Title and Question Generation
+  - Arabic Paraphrasing and Transliteration
+  - Arabic Code-Switched Translation
+---
 # AraT5v2-base-1024
 
 ## What's new?
-- **More data.** AraT2v2 trained on multiple varieties of Arabic data.
+- **More data.** AraT5v2-base-1024 trained on multiple varieties of Arabic data.
 - **Large sequence length.** We increase the sequence length from 512 to 1024 in this version.
-- **Converge faster.** AraT5v2 converges more than 10x compared with the previous version (AraT5-base.
-- **Extra IDs.**  AraT5v2 supports 100 sentinel tokens (a.k.a unique mask tokens).
+- **Converge faster.** AraT5v2-base-1024 converges more than 10x compared with the previous version (AraT5-base.
+- **Extra IDs.**  AraT5v2-base-1024 supports 100 sentinel tokens (a.k.a unique mask tokens).
 
 ```diff
 - We recommend using this version (AraT5v2-base-1024) instead of the previous version (AraT5-base).
 ```
 
 
+
+
+
+# Citation
+
+If you use our models (AraT5v2-base-1024, 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{nagoudi2022_arat5,
+@inproceedings{nagoudi-etal-2022-arat5,
+    title = "{A}ra{T}5: Text-to-Text Transformers for {A}rabic Language Generation",
+    author = "Nagoudi, El Moatez Billah  and
+      Elmadany, AbdelRahim  and
+      Abdul-Mageed, Muhammad",
+    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
+    month = may,
+    year = "2022",
+    address = "Dublin, Ireland",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2022.acl-long.47",
+    pages = "628--647",
+    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.",
+}
+