Update README.md

README.md

@@ -29,12 +29,8 @@ Our data has been collected by annotating tweets from a broad range of topics. I
 
 ## Performance
 
-We evaluate our performance using [SENTIPOLC16 Evalita](http://www.di.unito.it/~tutreeb/sentipolc-evalita16/). We collapsed the FEEL-IT classes into 2 by mapping joy to the *positive* class and anger, fear and sadness into the *negative* class. We compare three different training dataset combinations to understand whether it is better to train on FEEL-IT, SP16, or both by testing on the SP16 test set.
-
-
-This dataset comes with a training set and a testing set and thus we can compare the performance of different training datasets on the SENTIPOLC test set. 
-
-We use the fine-tuned UmBERTo model. The results show that FEEL-IT can provide better results on the SENTIPOLC test set than those that can be obtained with the SENTIPOLC training set. 
+We evaluate our performance using [SENTIPOLC16 Evalita](http://www.di.unito.it/~tutreeb/sentipolc-evalita16/). We collapsed the FEEL-IT classes into 2 by mapping joy to the *positive* class and anger, fear and sadness into the *negative* class. We compare three different experimental configurations training on FEEL-IT, SENTIPOLC16, or both by testing on the SENTIPOLC16 test set.
+The results show that training on FEEL-IT can provide better results on the SENTIPOLC16 test set than those that can be obtained with the SENTIPOLC16 training set.
 
 | Training Dataset | Macro-F1 | Accuracy
 | ------ | ------ |------ |