Attention Is All You Need
← Back to topic
Authors: Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin
Year: 2017
Journal: NeurIPS
DOI: 10.48550/arXiv.1706.03762
Publisher: https://arxiv.org/abs/1706.03762
Keywords: transformer, attention, neural machine translation
Abstract
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks. We propose a new simple network architecture the Transformer based solely on attention mechanisms.
Cite this paper
bibtex
@misc{transformer2017,
title = {Attention Is All You Need},
author = {Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin},
year = {2017},
journal = {NeurIPS},
doi = {10.48550/arXiv.1706.03762},
url = {https://doi.org/10.48550/arXiv.1706.03762},
}