Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.
1.48k
stars
368
forks
source link
Why do you have to use a dense layer to make the dim of input is the same as # of tags? #16
Closed
MilesQLi closed 6 years ago
Why can't you just use different dim for x from # of tags?