Table 5 LSTM parameter settings
From: De-identifying free text of Japanese electronic health records
Word embedding size | 200 |
Character embedding size | 100 |
Hidden layer of character | 100 |
Hidden layer of LSTM | 300 |
Learning rate | 0.001 |
From: De-identifying free text of Japanese electronic health records
Word embedding size | 200 |
Character embedding size | 100 |
Hidden layer of character | 100 |
Hidden layer of LSTM | 300 |
Learning rate | 0.001 |
Journal of Biomedical Semantics