Yufeng Ma

icon company Yahoo Research icon location Sunnyvale icon location Research Scientist at Verizon Media interested in data/text mining, computer vision, deep learning and machine learning in general.

Results 2 issues of Yufeng Ma

postion encoding

1 comment

Are we supposing the same length for each sentence in the position encoding? https://github.com/dandelin/Dynamic-memory-networks-plus-Pytorch/blob/ad49955f907c03aade2f6c8ed13370ce7288d5a7/babi_main.py#L18 As in above, each sentence encoding is divided by the same number elen-1.

Concern on this line

https://github.com/mjc92/GetToThePoint/blob/e59c06de957d98cedab6a2eacc8d2d44dd1f3e33/model.py#L173 Why it's multiplied by attn_mask instead of mask?