Update README.md

README.md

@@ -27,9 +27,9 @@ This named entity recognition model detects medication attributes:
 - Route: e.g. *vía oral*, *i.v.*
 
 The model achieves the following results on the test set (when trained with the training and development set; results are averaged over 5 evaluation rounds):
-- Precision: 0.842 (±0.008)
-- Recall: 0.886 (±0.013)
-- F1: 0.864 (±0.007)
+- Precision: 0.853 (±0.008)
+- Recall: 0.890 (±0.014)
+- F1: 0.871 (±0.008)
 - Accuracy: 0.997 (±0.001)
 
 
@@ -100,16 +100,16 @@ The following hyperparameters were used during training:
 
 |   Precision    |     Recall     |       F1       |    Accuracy    |
 |:--------------:|:--------------:|:--------------:|:--------------:|
-| 0.842 (±0.008) | 0.886 (±0.013) | 0.864 (±0.007) | 0.997 (±0.001) |
+| 0.853 (±0.008) | 0.890 (±0.014) | 0.871 (±0.008) | 0.997 (±0.001) |
 
 
 **Results per class (test set; average and standard deviation of 5 rounds with different seeds)**  
 
 | Class      |   Precision    |     Recall     |       F1       |  Support  |
 |:----------:|:--------------:|:--------------:|:--------------:|:---------:|
-| Dose       | 0.816 (±0.029) | 0.876 (±0.022) | 0.845 (±0.012) |    313    |
+| Dose       | 0.812 (±0.030) | 0.873 (±0.022) | 0.841 (±0.014) |    314    |
 | Form       | 0.818 (±0.009) | 0.883 (±0.023) | 0.849 (±0.013) |     65    |
-| Route      | 0.883 (±0.030) | 0.898 (±0.011) | 0.891 (±0.018) |    264    |
+| Route      | 0.916 (±0.032) | 0.911 (±0.012) | 0.913 (±0.019) |    270    |
 
 
 ### Framework versions