How Much Self-Attention Do We Needƒ Trading Attention for Feed-Forward Layers

Summary

This is a publication. If there is no link to the publication on this page, you can try the pre-formated search via the search engines listed on this page.

Authors: Kazuki Irie, Alexander Gerstenberger, Ralf Schluter, Hermann Ney

Journal title: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Journal publisher: IEEE

Published year: 2020

Published pages: 6154-6158

DOI identifier: 10.1109/icassp40776.2020.9054324

ISBN: 978-1-5090-6631-5