Losing heads in the lottery: Pruning transformer attention in neural machine translation (2020)

First Author: Behnke M.
Attributed to:  Peta-5: A National Facility for Petascale Data Intensive Computation and Analytics funded by EPSRC

Abstract

No abstract provided

Bibliographic Information

Type: Other

Parent Publication: EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference