Attention is Not Only a Weight: Analyzing Transformers with Vector Norms.

Goro Kobayashi Tatsuki Kuribayashi Sho Yokoi Kentaro Inui

Published in: EMNLP (1) (2020)

Keyphrases

multi agent systems
feature vectors
visual attention
information retrieval
feature selection
multiscale
weight function
neural network
artificial intelligence
case study
image sequences
multiresolution
eye tracking
total weight