From: B-LBConA: a medical entity disambiguation model based on Bio-LinkBERT and context-aware mechanism
Hyperparameter | Value |
---|---|
Character embedding dimension | 128 |
Context sentence length | 100 |
Learning rate | 0.001 |
Decay rate | 0.05 |
Batch size | 128 |
Dropout | 0.1 |
Epochs | 30 |
Hinge | 0.1 |
Top k | 50 |