Do concated size of the last layer equal to label_alpha table size ?

[HTMLgtMK]

1. As parameters listed in the utils/data.py , the label_dim equal to HP_hidden_dim, which specified to 200.
2. The output size of the LAN layer in the last layer is the size of [HP_hidden_dim, label_dim], that is 2*HP_hidden_dim.
3. After this, if we make use_crf = False , Do the concated size of the last layer eq to label_alpha size?
   Or make use_crf = True, how to make the output teasor with size (batch, seq_len, HP_hidden_dim) to the emission probability ?

Could Anyone give me some advise ? Thx !

[Nealcly]

Sorry for the late reply.

The output size of the last LAN layer is hidden_dim rather than 2*hidden_dim, because we only use attention weights for local classifier.

I have not tried to add CRF layer to our model. It should be worked if you fed attention weights directly (batch, seq_len, HP_hidden_dim).