[PDF]
Attention is all you need
A Vaswani, N Shazeer, N Parmar - Advances in Neural Information Processing Systems, 2017 - proceedings.neurips.cc
Abstract Transformer models replace recurrence with attention.
Cited by 145,321
Related articles
All 42 versions
[CITATION]
A citation-only record
J Doe, A Roe - 2021
A record without a publisher landing page.
[PDF]
[PDF]
A current Scholar result
A Author, B Author - Proceedings of ExampleConf, 2024 - arxiv.org
Current Scholar full-text container.
Cited by 7