Update README.md

README.md

@@ -13,7 +13,7 @@ widget:
 <img src="https://raw.githubusercontent.com/UBC-NLP/marbert/main/ARBERT_MARBERT.jpg" alt="drawing" width="25%" height="25%" align="right"/>
 
 **ARBERTv2** is the updated version of ARBERT model described in our **ACL 2021 paper** **["ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic"](https://aclanthology.org/2021.acl-long.551.pdf)**. 
-**ARBERTv2** is presented on our paper ["ORCA: A Challenging Benchmark for Arabic Language Understanding"](https://arxiv.org/abs/2212.10758)
+**ARBERTv2** is presented in our paper ["ORCA: A Challenging Benchmark for Arabic Language Understanding"](https://arxiv.org/abs/2212.10758)
 **ARBERTv2** is trained on MSA data **243 GB** of text and **27.8B tokens**.