Statements (25)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
arXiv preprint
|
| gptkbp:allows |
The paper proposes the Transformer, a novel neural network architecture based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.
|
| gptkbp:author |
gptkb:Illia_Polosukhin
gptkb:Łukasz_Kaiser gptkb:Aidan_N._Gomez gptkb:Ashish_Vaswani gptkb:Jakob_Uszkoreit gptkb:Llion_Jones gptkb:Niki_Parmar gptkb:Noam_Shazeer |
| gptkbp:category |
cs.CL
stat.ML |
| gptkbp:citation |
over 100,000 papers
|
| https://www.w3.org/2000/01/rdf-schema#label |
2004.05150
|
| gptkbp:influenced |
gptkb:T5
gptkb:BERT gptkb:GPT many transformer-based models |
| gptkbp:language |
English
|
| gptkbp:pdf |
https://arxiv.org/pdf/1706.03762.pdf
|
| gptkbp:publicationDate |
2017-06-12
|
| gptkbp:title |
gptkb:Attention_Is_All_You_Need
|
| gptkbp:url |
https://arxiv.org/abs/1706.03762
|
| gptkbp:bfsParent |
gptkb:Longformer
|
| gptkbp:bfsLayer |
6
|