Memory-efficient Transformers via Top-k Attention Ankit Gupta author Guy Dar author Shaya Goodman author David Ciprut author Jonathan Berant author 2021-11 text Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing Nafise Sadat Moosavi editor Iryna Gurevych editor Angela Fan editor Thomas Wolf editor Yufang Hou editor Ana Marasović editor Sujith Ravi editor Association for Computational Linguistics Virtual conference publication gupta-etal-2021-memory 10.18653/v1/2021.sustainlp-1.5 https://aclanthology.org/2021.sustainlp-1.5/ 2021-11 39 52