The only chance to understand: machine translation of the severely endangered low-resource languages of Eurasia - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

The only chance to understand: machine translation of the severely endangered low-resource languages of Eurasia

Résumé

Numerous machine translation systems have been proposed since the appearance of this task. Nowadays, new large language modelbased algorithms show results that sometimes overcome human ones on the rich-resource languages. Nevertheless, it is still not the case for the low-resource languages, for which all these algorithms did not show equally impressive results. In this work, we want to compare 3 generations of machine translation models on 7 low-resource languages and make a step further by proposing a new way of automatic parallel data augmentation using the state-ofthe-art generative model.
Fichier principal
Vignette du fichier
final_loresmt_paper.pdf (655.39 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03774644 , version 1 (11-09-2022)

Identifiants

  • HAL Id : hal-03774644 , version 1

Citer

Anna Mossolova, Kamel Smaïli. The only chance to understand: machine translation of the severely endangered low-resource languages of Eurasia. The Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT), COLING 2022, Oct 2022, Gyeongju, South Korea. ⟨hal-03774644⟩
46 Consultations
64 Téléchargements

Partager

Gmail Facebook X LinkedIn More