关于bilinear attention的疑问

liuwei1206 / LEBERT

Code for the ACL2021 paper "Lexicon Enhanced Chinese Sequence Labelling Using BERT Adapter"

338 stars 60 forks source link

Closed yikedouer closed 3 years ago

yikedouer commented 3 years ago

请问为什么使用了bilinear attention？ word embedding已经通过non-linear transformation与char embedding做到了维度对齐，是出于什么考虑使用了bilinear attention呢？

liuwei1206 commented 3 years ago

Hi,

I would like to recommend you to read the original paper, in which I have already shown my motivation to use bilinear attention.

Wei