From 4c6b21805647f3a96737a50390a4c3e9463d8ef7 Mon Sep 17 00:00:00 2001
From: Ali Safaya <alisafaya@gmail.com>
Date: Mon, 25 May 2020 22:12:23 +0300
Subject: [PATCH] Update README.md (#4556)

---
 model_cards/asafaya/bert-base-arabic/README.md | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/model_cards/asafaya/bert-base-arabic/README.md b/model_cards/asafaya/bert-base-arabic/README.md
index 2c370537..084ffb58 100644
--- a/model_cards/asafaya/bert-base-arabic/README.md
+++ b/model_cards/asafaya/bert-base-arabic/README.md
@@ -6,6 +6,17 @@ language: arabic
 
 Pretrained BERT base language model for Arabic
 
+_If you use this model in your work, please cite this paper (to appear in 2020):_
+
+```
+@inproceedings{
+  title={KUISAIL at SemEval-2020 Task 12: BERT-CNN for Offensive Speech Identification in Social Media},
+  author={Safaya, Ali and Abdullatif, Moutasem and Yuret, Deniz},
+  booktitle={Proceedings of the International Workshop on Semantic Evaluation (SemEval)},
+  year={2020}
+}
+```
+
 ## Pretraining Corpus
 
 `arabic-bert-base` model was pretrained on ~8.2 Billion words: