Utilisation des réseaux de neurones récurrents pour la projection interlingue d'étiquettes morpho-syntaxiques à partir d'un corpus parallèle

Résumé : In this paper, we propose a method to automatically induce linguistic analysis tools for languages that have no labeled training data. This method is based on cross-language projection of linguistic annotations from parallel corpora. Our method does not assume any knowledge about foreign languages, making it applicable to a wide range of resource-poor languages. No word alignment information is needed in our approach. We use Recurrent Neural Networks (RNNs) as cross-lingual analysis tool. To illustrate the potential of our approach, we firstly investigate Part-Of-Speech (POS) tagging. Combined with a simple projection method (using word alignment information), it achieves performance comparable to the one of recently published approaches for cross-lingual projection. Mots-clés : Multilinguisme, transfert crosslingue, étiquetage morpho-syntaxique, réseaux de neurones récurrents.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [23 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01350115
Contributor : Laurent Besacier <>
Submitted on : Friday, July 29, 2016 - 4:25:59 PM
Last modification on : Thursday, April 4, 2019 - 10:18:05 AM
Document(s) archivé(s) le : Sunday, October 30, 2016 - 12:24:11 PM

File

taln-2015-court-032.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-01350115, version 1

Citation

Othman Zennaki, Nasredine Semmar, Laurent Besacier. Utilisation des réseaux de neurones récurrents pour la projection interlingue d'étiquettes morpho-syntaxiques à partir d'un corpus parallèle. TALN 2015, Jul 2015, Caen, France. ⟨hal-01350115⟩

Share

Metrics

Record views

235

Files downloads

471