Train/Decode speed comparation with CRF

[Freeshman]

Hello, your work is very great but I have a question about the speed comparation.
From your code published, when we use the CRF, in the seqlab.py file, the CRF layer only be used to calculate the loss in the neg_log_liklihood_loss function, but in the forward function, there is nothing with CRF layer. Did I miss something somewhere ? Hope hear your reply, thank you very much.

[Nealcly]

Hi, thanks for the kind words about the paper.
The current version does not support CRF baseline. This is because I forgot to add the baseline code before uploading. I will modify it as soon as possible.