Skip to Main content Skip to Navigation
Conference papers

Modèles neuronaux hybrides pour la modélisation de séquences : le meilleur de trois mondes

Abstract : We propose a neural architecture with the main characteristics of the most successful neural models of the last years : bidirectional RNNs, encoder-decoder, and the Transformer model. Evaluation on three sequence labelling tasks yields results that are close to the state-of-the-art for all tasks and better than it for some of them, showing the pertinence of this hybrid architecture for this kind of tasks.
Document type :
Conference papers
Complete list of metadata

Cited literature [46 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02157160
Contributor : Loïc Grobol Connect in order to contact the contributor
Submitted on : Wednesday, September 11, 2019 - 11:05:25 AM
Last modification on : Friday, October 15, 2021 - 1:40:08 PM

File

2019_TALN.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

  • HAL Id : hal-02157160, version 2

Citation

Marco Dinarelli, Loïc Grobol. Modèles neuronaux hybrides pour la modélisation de séquences : le meilleur de trois mondes. TALN-RECITAL 2019 - 26ème Conférence sur le Traitement Automatique des Langues Naturelles, ATALA, Jul 2019, Toulouse, France. ⟨hal-02157160v2⟩

Share

Metrics

Record views

155

Files downloads

524