Skip to main content

Advertisement

Table 4 Results of the hyperparameter tuning, the last column shows the selected value for each language

From: Recent advances in Swedish and Spanish medical entity recognition in clinical texts using deep neural approaches

HyperparameterEvaluated valuesBest Swedish/Spanish
Batch size10, 20, 30, 40, 50, 10030/10
Nr. of hidden units, LSTM100, 200, 300, 400300/300
Nr. of hidden units, char.5, 50, 100, 150, 200100/100
Learning rate0.01, 0.005, 0.001, 0.0005, 0.000050.005/0.005
Drop-out0.5, 0.80.5/0.5
Dimension character embeddings50, 100, 150, 200, 300100/300
Dimension word embeddings100, 300300/300