Update README.md

README.md

@@ -8,7 +8,7 @@ widget:
 
 
 The training dataset of this model  consists of 23 million tweets in Greek, of approximately 5000 users in total, spanning from 2008 to 2018.
-The model has been trained to support the work for the paper [Multimodal Hate Speech Detection in Greek Social Media (preprint v1)](https://www.preprints.org/manuscript/202103.0390/v1 ) 
+The model has been trained to support the work for the paper [Multimodal Hate Speech Detection in Greek Social Media](https://www.mdpi.com/2414-4088/5/7/34) 
 
 
 ## Load the pretrained model