Survey of Low-Resource Machine Translation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Computational Linguistics Year : 2022

Survey of Low-Resource Machine Translation

Abstract

We present a survey covering the state of the art in low-resource machine translation (MT) research. There are currently around 7,000 languages spoken in the world and almost all language pairs lack significant resources for training machine translation models. There has been increasing interest in research addressing the challenge of producing useful translation models when very little translated training data is available. We present a summary of this topical research field and provide a description of the techniques evaluated by researchers in several recent shared tasks in low-resource MT.
Fichier principal
Vignette du fichier
haddow-et-al-2022-low-resource-survey.pdf (415.4 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03479757 , version 1 (14-12-2021)
hal-03479757 , version 2 (14-03-2022)
hal-03479757 , version 3 (01-11-2022)

Identifiers

  • HAL Id : hal-03479757 , version 3

Cite

Barry Haddow, Rachel Bawden, Antonio Valerio Miceli Barone, Jindřich Helcl, Alexandra Birch. Survey of Low-Resource Machine Translation. Computational Linguistics, 2022, 48 (3), pp.673--732. ⟨hal-03479757v3⟩
116 View
491 Download

Share

Gmail Facebook X LinkedIn More