Difference in paper and codes.

[caoxu915683474]

https://github.com/abisee/pointer-generator/blob/a7317f573d01b944c31a76bde7218bcfc890ef6a/attention_decoder.py#L173

Hi, abisee! I am confused about the codes in this line. In your paper, the function is V[s_t, h*_t] + b But in the codes, you use rnn_output instead.

Thanks for your help!

[mmlynarik]

It's not a difference actually. The cell output is in fact identical to s_t, which is hidden state of current lstm cell. See https://github.com/abisee/pointer-generator/blob/a7317f573d01b944c31a76bde7218bcfc890ef6a/attention_decoder.py#L152