Updated with results on the train/val dataset.

paper/40_experiments.tex

@@ -75,15 +75,24 @@ The two modeles where combined to create the final pipeline.
 We tested both NER models in the final pipeline, as their performance differs significantly.
 As both NEN models performe similary, we used the word and extended ICD-10 classification model in the final pipeline.
 The results obtained during training are presented in Table \ref{tab:final_train}.
+Results obtained on the evaluation dataset are shown in Table \ref{tab:final_test}
 
 \begin{table}[]
 \centering
-\begin{tabular}{l|l|l|l|l|l}
+\begin{tabular}{|l|l|l|l|}
 Model &  Precision & Recall & F-1\\
 S2S balanced + ICD-10 extended & 0.73 & 0.61 & 0.61 \\
 S2S extended + ICD-10 extended & 0.74 & 0.62 & 0.63 \\
 \end{tabular}
 \caption{Final Pipeline Evaluation}
 \label{tab:final_train}
+\begin{tabular}{|l|l|l|l|}
+Model &  Precision & Recall & F-1\\
+S2S balanced + ICD-10 extended &  &  & \\
+S2S extended + ICD-10 extended &  &  & \\
+\end{tabular}
+\caption{Final Pipeline Evaluation}
+\label{tab:final_test}
+
 \end{table}