search

mjc92 / CopyNet

An implementation of "Incorporating copying mechanism in sequence-to-sequence learning"
153 stars 46 forks source link

Question about selective read #3

Open JuliRao opened 5 years ago

JuliRao commented 5 years ago

I've read the code in models/copynet.py. I think in the third step 'get weighted attention to use for predicting next word', input_idx(y_t) should be used instead of inputidx(y(t-1)), which is then used to generate y_(t+1).

SilverLiningSL commented 4 years ago

Have you figured it out? This is also where I get puzzled.