Tutorial 3 : Aligment Model not the same as the paper

[xxoospring]

This is the alignment model in paper which has three single layer MLP: v, W and U, but in Tutorial 3 implementations，we cat vector S and encoder output h, and pass them through one MLP.

[bentrevett]

Not sure how I messed this up. Will look into it further. Thanks for pointing it out.

[yipliu]

This is the alignment model in paper which has three single layer MLP: v, W and U, but in Tutorial 3 implementations，we cat vector S and encoder output h, and pass them through one MLP.

Hi xxoospring, Could you share your code with the Tutorial 3