Update README.md

README.md

@@ -11,16 +11,8 @@ widget:
 This is a model to detect treatment and disease mentions in texts from health domains.
 The dataset used for training consists of [PubMed's abstracts](https://www.ncbi.nlm.nih.gov/guide/howto/dwn-records/) and [tweets](https://developer.twitter.com/en/use-cases/do-research) with disease mentions, which are publicly available. It has been semi-automatically labeled with a set of regex rules made ad hoc to find treatment-disease links.
 
-# Label set
-Abbreviation|Description
--|-
-O| Outside of a named entity
-t | Treatment
-d | Disease
+The label ```t``` is used for treatment (medication, procedures, etc.) and ```d``` for disease mentions.
 
-# Performance (Seqeval metric)
-precision|recall|f1
--|-|-
-0.92|0.95|0.93
+The current F1 score (Seqeval) is 0.91