Login / Signup
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned.
Elena Voita
David Talbot
Fedor Moiseev
Rico Sennrich
Ivan Titov
Published in:
ACL (1) (2019)
Keyphrases
</>
magnetic recording
general purpose
wavelet transform
real time
databases
expert systems
multiresolution
computer simulation
visual attention
focus of attention