README

README.md

@@ -96,21 +96,17 @@ print(pii_classes)
 ### Testing Data, Factors & Metrics
 
 #### Testing Data
-1. We developed an in house testset that we evaluate the model on. The test set was manually annotated to ensure high quality of the test set. 
+1. We developed an in house testset that we evaluate the model on. The test set was manually annotated to ensure high quality of the test set. The test set mainly comprises of financial documents , contracts etc across all the 7 languages, covering all the classes.
 
 
 #### Metrics
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+1. We used precision , recall and F1 score to evaluate the models output with the ground truth. 
 
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
+We consider precision and recall to be:
 
+Precision: The ratio of correctly identified PII instances to the total identified instances.
+Recall: The ratio of correctly identified PII instances to the total actual instances in the dataset.
 
 ## Model Card Authors