Feature: Train new model with improved MIP detection

Author: strangetom

README.md

@@ -48,13 +48,13 @@ The model has the following accuracy on a test data set of 20% of the total data
 
 ```
 Sentence-level results:
-	Accuracy: 94.90%
+	Accuracy: 94.97%
 
 Word-level results:
-	Accuracy 97.88%
-	Precision (micro) 97.86%
-	Recall (micro) 97.88%
-	F1 score (micro) 97.86%
+	Accuracy 97.91%
+	Precision (micro) 97.89%
+	Recall (micro) 97.91%
+	F1 score (micro) 97.89%
 ```
 
 ## Development

ingredient_parser/en/data/ModelCard.en.md

@@ -124,11 +124,11 @@ The model has the following performance metrics:
 
 | Word level accuracy | Sentence level accuracy |
 | ------------------- | ----------------------- |
-| 97.88 ± 0.23%       | 94.90 ± 0.56%           |
+| 97.91 ± 0.23%       | 94.97 ± 0.56%           |
 
 These metrics were determined by executing 20 training/evaluation cycles and calculating the mean and standard deviation for the two metrics across all cycles. The uncertainty values provided represent the 99.7% confidence bounds (i.e. 3x standard deviation). The uncertainty is due to the randomisation of the selection of training and evaluation data whenever the model is trained.
 
-The random seed used for the train/test split for this model was 271938947.
+The random seed used for the train/test split for this model was 384522096.
 
 ## Ethical Considerations