Vocabulary size of z/R in output module of EntNet

[shtoshni]

Hi,

I have been looking at the code and I'm not sure why the output vocabulary size consists of both the word & key embeddings when the key is not tied -- link to code. The step is followed by a narrow operation limiting the logsoftmax to only the words. Is there any reason for the design choice or we can get rid of the extra rows from z/R.