Table 3 Overview of input text length and its impact on coding performance.

From: Multi-label text classification via secondary use of large clinical real-world data sets

# of Tokens

> 512

\(<=\) 512

Model

Precision

Recall

F1-measure

MAP

Precision

Recall

F1-measure

MAP

medBERT.de

0.378

0.751

0.463

0.837

0.245

0.946

0.377

0.882

surgeryBERT.at

0.374

0.741

0.459

0.820

0.241

0.937

0.372

0.869

fastText

0.403

0.791

0.493

0.840

0.241

0.935

0.372

0.870

CNN

0.375

0.743

0.460

0.817

0.237

0.923

0.366

0.853

SVM

0.418

0.795

0.505

0.872

0.235

0.911

0.362

0.869

LR

0.348

0.661

0.421

0.768

0.220

0.855

0.339

0.808

Back to article page