Skip to main content

Table 4 The effectiveness of the integrated attention mechanisms according to mean F1 scores for 30 different random seeds

From: Relation extraction between bacteria and biotopes from biomedical texts with attention mechanisms and domain-specific contextual representations

ModelPEF1 score
FullsSDPs MeanSDMinMax
BLSTMCNN45.962.8742.0952.19
BLSTMCNN48.494.7638.7555.40
BLSTM-AttnCNN49.023.6242.0356.51
BLSTM-EAttnCNN50.243.7243.1455.72
BLSTM-EAttnMAttn53.422.5146.6756.70
  1. All of the highest scores are highlighted in bold except for the SD. The first-row results derive from the best results of previous experiments (i.e., the last row in Table 3). Note: “PE” denotes positional encoding, “Attn” denotes the use of only Additive attention, “EAttn” denotes the use of both Additive and Entity-Oriented attentions, and “MAttn” denotes the use of Multi-Head attention