postion encoding

[yufengm]

Are we supposing the same length for each sentence in the position encoding?

Dynamic-memory-networks-plus-Pytorch/babi_main.py

Line 18 in ad49955

l = [[(1 - s/(slen-1)) - (e/(elen-1)) * (1 - 2*s/(slen-1)) for e in range(elen)] for s in range(slen)]

As in above, each sentence encoding is divided by the same number elen-1.

[AveryLiu]

I suppose you could pad the variated sentences length to a fixed number in the preprocessing step before feeding them into the model.