Creating and sharing knowledge for telecommunications

Predicting Attention Sparsity in Transformers

Treviso, M. V. T. ; Gois, A. ; Fernandes, P. ; Fonseca, E.F. ; Martins, A.

Predicting Attention Sparsity in Transformers, Proc Annual Meeting of the Association for Computational Linguistics - ACL, Dublin, Ireland, Vol. , pp. - , May, 2022.

Digital Object Identifier:

Abstract