Linformer approximates self-attention with a low-rank projection to achieve O(n) time and space complexity while matching Transformer accuracy on standard NLP tasks.
Recursive deep models for semantic compositionality over a sentiment treebank
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2020 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Linformer: Self-Attention with Linear Complexity
Linformer approximates self-attention with a low-rank projection to achieve O(n) time and space complexity while matching Transformer accuracy on standard NLP tasks.