Table 2 Hyperparameters
From: A document level neural model integrated domain knowledge for chemical-induced disease relations
Parameter Name | Value |
|---|---|
l1: Word emb.Size | 100 |
l2: POS emb.Size | 10 |
m: Knowledge emb.Size | 200 |
The number n1 of sentences in an article | 30 |
The number n2 of words in a sentence | 120 |
The window size w for CNN | 5 |
The number f of filters for CNN | 300 |
Mini-batch | 8 |
The number of hidden units of two LSTMs | 220,440 |
The learning rate lr of RMSprop | 0.001 |
The dropout rate | 0.5 |