Update README.md

README.md

@@ -33,7 +33,7 @@ Measurement on validation sets of the KLUE benchmark datasets
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62ce3886a9be5c195564fd71/50jMYggkGVUM06n2v1Hxm.png)
 
 ### Limitations
-While our model achieves great results without further pretraining, direct pretraining can further refine position representations, making it even more precise.
+While our model achieves great results without further pretraining, direct pretraining can further refine positional representations.
 
 ## Citation Information