Attention Weight of padding tokens?

SeoSangwoo / Attention-Based-BiLSTM-relation-extraction

Tensorflow Implementation of "Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification" (ACL 2016)

http://www.aclweb.org/anthology/P16-2034

Apache License 2.0

430 stars 139 forks source link

Open vhientran opened 5 years ago

vhientran commented 5 years ago

Please let me know if this model architecture calculates attention weights for padding tokens or not.