Attention Is All You Need
paperAuthors
Credibility Rating
Good quality. Reputable source with community review or editorial standards, but less rigorous than peer-reviewed venues.
Rating inherited from publication venue: arXiv
Data Status
Abstract
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.
Cited by 2 pages
| Page | Type | Quality |
|---|---|---|
| Large Language Models | Concept | 62.0 |
| Dense Transformers | Concept | 58.0 |
Cached Content Preview
[1706.03762] Attention Is All You Need
-->
Computer Science > Computation and Language
arXiv:1706.03762 (cs)
[Submitted on 12 Jun 2017 ( v1 ), last revised 2 Aug 2023 (this version, v7)]
Title: Attention Is All You Need
Authors: Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , Illia Polosukhin View a PDF of the paper titled Attention Is All You Need, by Ashish Vaswani and 7 other authors
View PDF
HTML (experimental)
Abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.
Comments:
15 pages, 5 figures
Subjects:
Computation and Language (cs.CL) ; Machine Learning (cs.LG)
Cite as:
arXiv:1706.03762 [cs.CL]
(or
arXiv:1706.03762v7 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.1706.03762
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Llion Jones [ view email ]
[v1]
Mon, 12 Jun 2017 17:57:34 UTC (1,102 KB)
[v2]
Mon, 19 Jun 2017 16:49:45 UTC (1,125 KB)
[v3]
Tue, 20 Jun 2017 05:20:02 UTC (1,125 KB)
[v4]
Fri, 30 Jun 2017 17:29:30 UTC (1,124 KB)
[v5]
Wed, 6 Dec 2017 03:30:32 UTC (1,124 KB)
[v6]
Mon, 24 Jul 2023 00:48:54 UTC (1,124 KB)
[v7]
Wed, 2 Aug 2023 00:41:18 UTC (1,124 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Attention Is All You Need, by Ashish Vaswani and 7 other authors View PDF
HTML (experimental)
TeX Source
view license
Current browse context: cs.CL
< prev
|
next >
new
|
recent
| 2017-06
Change to browse by:
cs
cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
123 blog links
( what is this? )
... (truncated, 6 KB total)a7468c6851652691 | Stable ID: YmIxNjlhMj