Hi, I like your work, and your code is decent. But I'm a little confused about the tensor calculation in matching. In match_utils.py, function multi_perspective_match:
Why only tf.multiply(repres1_flat, mp_cosine_params) , but not tf.multiply(repres2_flat, mp_cosine_params) as well ? In your paper, W is multiplied by both v1 and v2.
Hi, I like your work, and your code is decent. But I'm a little confused about the tensor calculation in matching. In match_utils.py, function multi_perspective_match:
Why only
tf.multiply(repres1_flat, mp_cosine_params)
, but nottf.multiply(repres2_flat, mp_cosine_params)
as well ? In your paper, W is multiplied by both v1 and v2.Looking forward to reply, thanks!