On the Validity of Self-Attention as Explanation in Transformer Models.

Gino Brunner Yang Liu Damián Pascual Oliver Richter Roger Wattenhofer

Published in: CoRR (2019)

Keyphrases

artificial neural networks
statistical models
historical data
structural model
machine learning
social networks
e learning
website
multi agent
expert systems
prior knowledge
probabilistic model
visual attention
modeling framework
generating explanations