Update README.md

README.md

@@ -12,8 +12,8 @@ widget:
 
 A BERT model trained on the synthetic literary NER context retrieval dataset [Amalvy et. al, 2023](https://aclanthology.org/2023.emnlp-main.642/). 
 
-To use this model, construct a text of the form `NER-sentence [SEP] context-sentence`.
-The model should predict the positive class if `context-sentence` is useful to predict `NER-sentence`, and the negative class otherwise.
+To use this model, construct a text of the form **NER-sentence [SEP] context-sentence**.
+The model should predict the positive class if **context-sentence** is useful to predict **NER-sentence**, and the negative class otherwise.
 
 
 # Performance Metrics