Attention Is All You Need

DOI10.48550/ARXIV.1706.03762MaRDI QIDQ102015arXivFDO

Authors Illia Polosukhin, Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser

Publication date 12 June 2017

Published in arXiv

Full work available at URL https://doi.org/10.48550/ARXIV.1706.03762

arXiv classification

cs.CLcs.LG

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 in

(15)

• attention
• transformer
• Modelling Opinion Dynamics at Scale with Deep MARL
• Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning
• Time-Invariant Neural Operators with Applications in Solving Time-Dependent PDEs
• Automated Numerical Stability Analysis of Deep Learning Operators
• It's All Just Vectorization: einx, a Universal Notation for Tensor Operations
• Physics-informed token transformer methodology for nonlinear balance laws. I. Schwarzschild--Burgers fluid flows
• Training-Free Universal Approximation by Prompting Random Transformers
• Beyond PINNs: A Unified Gauss--Newton and Petrov--Galerkin Framework for Neural and Hybrid PDE Solvers
• Stiefel Attention: When the Geometry of Transformer Projection Matrices Dominates Optimizer Choice---and When It Does Not
• KATOsuper: Surrogate-accelerated neural topology optimization with sensitivity-consistent Fourier neural operators
• Latent Twin Operator
• LampAttention: Look-Ahead Mixed-Precision FlashAttention for Dedicated Accelerators
• Inferring physical fields in coupled systems with unknown parameters from incomplete observations using physics-constrained attentive neural operators

This page was built for publication: Attention Is All You Need

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q102015)