Skip to main content


Table 2 Hyper-parameter settings

From: A neural joint model for entity and relation extraction from biomedical text

Type Hyper-parameter
Training α=0.03,λ=10−8
Embedding dim(emb(w i ))=200
  \(dim(emb(p_{i}), emb(d_{i})~\text {or}~emb(l^{e}_{i}))=25\)
CNN dim(emb(c))=25,C=3
  dim(r w )=25
Bi-LSTM-RNN (Entity) \(dim(\overrightarrow {h}_{i})\) or \(dim(\overleftarrow {h}_{i})=100\)
Bi-LSTM-RNN (Relation) dim( h a , h b , h a or h b )=100
  dim(h r)=100
  1. dim denotes vector dimensions and emb denotes feature embeddings