Skip to Main content Skip to Navigation
Conference papers

Traduction automatique du japonais vers le français : Bilan et perspectives

Abstract : In this paper, we discuss the feasability of a neural machine translation system from Japanese to French, which would be able to obtain results that are equivalent to the state of the art. We first describe the state of the art for Ja>Fr and see many improvements compared to statistical machine translation. Second, we evaluate one free open baseline, OpenNMT, which achieves encouraging results. Based on these experiments, we suggest some ways to improve the results, taking into account the lack of improved and large corpora.
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01796313
Contributor : Raoul Blin <>
Submitted on : Saturday, May 19, 2018 - 6:15:20 PM
Last modification on : Wednesday, August 5, 2020 - 3:15:20 AM
Long-term archiving on: : Tuesday, September 25, 2018 - 5:13:38 AM

File

TALN2018_paper_28.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01796313, version 1

Relations

Citation

Raoul Blin. Traduction automatique du japonais vers le français : Bilan et perspectives. Traitement Automatique du Langage Naturel, May 2018, Rennes, France. ⟨hal-01796313⟩

Share

Metrics

Record views

193

Files downloads

236