Table 2: 

Hyperparameters used in the experiments.

NameValue
Word Embedding GloVe (PTB) / fastText (UD) 
BERT BERT-Base 
CNN window size 
CNN filters 30 
BiLSTM layers 
BiLSTM units 300 dimensions 
Optimization Adam 
Learning rate 0.001 
Rescaling factor τ 64 
Dropout ratio {0.1, 0.2, 0.3} 
NameValue
Word Embedding GloVe (PTB) / fastText (UD) 
BERT BERT-Base 
CNN window size 
CNN filters 30 
BiLSTM layers 
BiLSTM units 300 dimensions 
Optimization Adam 
Learning rate 0.001 
Rescaling factor τ 64 
Dropout ratio {0.1, 0.2, 0.3} 
Close Modal

or Create an Account

Close Modal
Close Modal