Skip to main content

Table 7 Average test accuracies in five-fold validation for knowledge representation learning

From: Incorporating representation learning and multihead attention to improve biomedical cross-sentence n-ary relation extraction

Method Ternary
  Single Cross
TransE 83.9 90.8
TransD 85.8 90.9
TransH 86.5 91.2
TransR 87.3* 91.9*