Survey of Low-Resource Machine Translation

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...

Full description

Saved in:
Bibliographic Details
Published in:Computational linguistics - Association for Computational Linguistics Vol. 48; no. 3; pp. 673 - 732
Main Authors: Haddow, Barry, Bawden, Rachel, Barone, Antonio Valerio Miceli, Helcl, Jindřich, Birch, Alexandra
Format: Journal Article
Language:English
Published: One Broadway, 12th Floor, Cambridge, Massachusetts 02142, USA MIT Press 01.09.2022
MIT Press Journals, The
Massachusetts Institute of Technology Press (MIT Press)
The MIT Press
Subjects:
Computation and Language
Computer Science
Languages
Machine translation
Polls & surveys
Training
Translation
ISSN:0891-2017, 1530-9312
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:2022
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0891-2017
1530-9312
DOI:10.1162/coli_a_00446