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.
Type de document :
Communication dans un congrès
CoNLL 2018 - Conference on Computational Natural Language Learning, Oct 2018, Brussels, Belgium. pp.1-11
Liste complète des métadonnées

Littérature citée [7 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01851612
Contributeur : Thoth Team <>
Soumis le : mardi 4 septembre 2018 - 09:39:06
Dernière modification le : jeudi 11 octobre 2018 - 08:48:02

Fichier

paper.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01851612, version 3

Collections

Citation

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.1-11. 〈hal-01851612v3〉

Partager

Métriques

Consultations de la notice

215

Téléchargements de fichiers

95