Skip to Main content Skip to Navigation
Conference papers

Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction

Abstract : Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention mechanism that recombines a fixed encoding of the source tokens based on the decoder state. We propose an alternative approach which instead relies on a single 2D convolutional neural network across both sequences. Each layer of our network re-codes source tokens on the basis of the output sequence produced so far. Attention-like properties are therefore pervasive throughout the network. Our model yields excellent results, outperforming state-of-the-art encoder-decoder systems, while being conceptually simpler and having fewer parameters.
Complete list of metadata

Cited literature [42 references]  Display  Hide  Download
Contributor : Thoth Team Connect in order to contact the contributor
Submitted on : Tuesday, September 4, 2018 - 9:39:06 AM
Last modification on : Thursday, January 20, 2022 - 5:26:11 PM
Long-term archiving on: : Wednesday, December 5, 2018 - 1:06:39 PM


Files produced by the author(s)


  • HAL Id : hal-01851612, version 3


Maha Elbayad, Laurent Besacier, Jakob Verbeek. Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction. CoNLL 2018 - Conference on Computational Natural Language Learning, Oct 2018, Brussels, Belgium. pp.97-107. ⟨hal-01851612v3⟩



Les métriques sont temporairement indisponibles