BriefGPT.xyz
Sep, 2019
跨 NLP 任务的注意力可解释性
Attention Interpretability Across NLP Tasks
HTML
PDF
Shikhar Vashishth, Shyam Upadhyay, Gaurav Singh Tomar, Manaal Faruqui
TL;DR
本文旨在通过一系列的NLP任务，人工评估实验等方式，全面解释神经网络模型中的注意力机制的可解释性，并证明了注意力的可解释性验证了两种观点。
Abstract
The
attention layer
in a
neural network
model provides insights into the model's reasoning behind its prediction, which are usually criticized for being opaque. Recently, seemingly contradictory viewpoints have e
→