Skip to Main content Skip to Navigation
Journal articles

Analyse syntaxique de langues faiblement dotées à partir de plongements de mots multilingues : Application au same du nord et au komi-zyriène

Abstract : This article presents an attempt to apply efficient parsing methods based on recur- sive neural networks to languages for which very few resources are available. We propose an original approach based on multilingual word embeddings acquired from different languages so as to determine the best language combination for learning. The approach yields competitive results in contexts considered as linguistically difficult.
Complete list of metadatas

Cited literature [49 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02268956
Contributor : Thierry Poibeau <>
Submitted on : Wednesday, August 21, 2019 - 11:38:55 PM
Last modification on : Thursday, September 5, 2019 - 10:40:03 AM
Document(s) archivé(s) le : Friday, January 10, 2020 - 11:14:55 AM

File

TAL59-3-Lim.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-02268956, version 1

Collections

Citation

Kyungtae Lim, Niko Partanen, Thierry Poibeau. Analyse syntaxique de langues faiblement dotées à partir de plongements de mots multilingues : Application au same du nord et au komi-zyriène. Traitement Automatique des Langues, ATALA, 2018, Traitement automatique des langues peu dotées, 59 (3), pp.67-91. ⟨hal-02268956⟩

Share

Metrics

Record views

68

Files downloads

77