Skip to main content

Table 2 Doc-level performance comparison over our proposed model without and with knowledge on the CDR dataset

From: Biomedical relation extraction via knowledge-enhanced reading comprehension

KBs Model P (%) R (%) F1 (%)
Without KBs
 Traditional ML ME [8] 62.00 55.10 58.30
Kernel-based SVM [24] 53.20 69.70 60.30
NN-based ML
 Relation classification CNN+SDP [6] 58.02 76.20 65.88
LSTM+CNN [25] 56.20 68.00 61.50
BRAN(Transformer) [3] 55.60 70.80 62.10
CNN+CNNchar [11] 57.00 68.60 62.30
GCNN [2] 52.80 66.00 58.60
 Sequence labeling Bio-Seq(LSTM+CRF) [23] 60.00 67.50 63.50
 Reading comprehension RC (Ours) 65.83 66.32 66.07
With KBs
 Traditional ML     
SVM+Rules(+CTD)[26] 68.15 66.04 67.08
SVM(+CTD+SIDER+MEDI+MeSH) [9] 65.80 68.57 67.16
Kernel-based models(+CTD) [10] 60.84 76.36 67.72
SVM(+Euretos KB) [27] 73.10 67.60 70.20
NN-based ML
 Relation classification CAN(+CTD) [7] 60.51 80.48 69.08
LSTM+CNN(+CTD) [4] 63.60 76.80 69.60
RPCNN(+CTD+SIDER+MEDI+MeSH fea) [5] 65.24 77.21 70.77
KCN(+CTD) [1] 69.65 72.98 71.28
 Reading comprehension KRC(+DCh-Miner) (Ours) 65.33 67.17 66.23
KRC(+CTD) (Ours) 71.93 70.45 71.18
  1. ‘fea’ denotes features