Skip to main content

Table 6 Performance comparison using different combinations of external training datasets

From: SBLC: a hybrid model for disease named entity recognition based on semantic bidirectional LSTMs and conditional random fields

Pre-Data Sets

Precision

Recall

F1

Wikipedia

0.842

0.838

0.840

PMC (full text)

0.866

0.856

0.861

PubMed (abstract)

0.847

0.838

0.843

PubMed (abstract) + PMC (full text)

0.866

0.858

0.862

Wikipedia+PubMed (abstract) + PMC (full text)

0.865

0.858

0.861

  1. The highest values are denoted in bold type