Update README.md

README.md

@@ -27,7 +27,7 @@ The EstBERT model is trained both on 128 and 512 sequence length of data. For tr
 
 ### Reference to cite
 
-(Tanvir et al, 2021)[https://aclanthology.org/2021.nodalida-main.2/]
+[Tanvir et al 2021](https://aclanthology.org/2021.nodalida-main.2)
 
 ### Why would I use?
 Overall EstBERT performs better in parts of speech (POS), name entity recognition (NER), rubric, and sentiment classification tasks compared to mBERT and XLM-RoBERTa. The comparative results can be found below;