Skip to main content

Table 3 Doc-level performance comparison over our proposed model without knowledge on the CHR dataset

From: Biomedical relation extraction via knowledge-enhanced reading comprehension

  Model P (%) R (%) F1 (%)
NN-based ML
 Relation classification CNN-RE [2] 81.2 87.3 84.1
RNN-RE [2] 83.0 90.1 86.4
GCNN [2] 84.7 90.5 87.5
 Reading comprehension RC (Ours) 93.5 93.0 93.3