Memory-efficient Transformers via Top-k Attention.

Ankit Gupta Guy Dar Shaya Goodman David Ciprut Jonathan Berant

Published in: SustaiNLP@EMNLP (2021)

Keyphrases

memory efficient
query processing
external memory
multiple sequence alignment
iterative deepening
data sets
user defined
integral image
information retrieval
learning algorithm
focus of attention
genetic algorithm
scoring function