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...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
The MIT Press
2022-06-01
|
Series: | Computational Linguistics |
Online Access: | http://dx.doi.org/10.1162/coli_a_00446 |
_version_ | 1797795406382366720 |
---|---|
author | Barry Haddow Rachel Bawden Antonio Valerio Miceli Barone Jindřich Helcl Alexandra Birch |
author_facet | Barry Haddow Rachel Bawden Antonio Valerio Miceli Barone Jindřich Helcl Alexandra Birch |
author_sort | Barry Haddow |
collection | DOAJ |
description | 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. |
first_indexed | 2024-03-13T03:17:26Z |
format | Article |
id | doaj.art-c67ef92aeb924e50a96fada3b039dfa7 |
institution | Directory Open Access Journal |
issn | 1530-9312 |
language | English |
last_indexed | 2024-03-13T03:17:26Z |
publishDate | 2022-06-01 |
publisher | The MIT Press |
record_format | Article |
series | Computational Linguistics |
spelling | doaj.art-c67ef92aeb924e50a96fada3b039dfa72023-06-25T14:50:05ZengThe MIT PressComputational Linguistics1530-93122022-06-0148310.1162/coli_a_00446Survey of Low-Resource Machine TranslationBarry HaddowRachel BawdenAntonio Valerio Miceli BaroneJindřich HelclAlexandra BirchWe 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.http://dx.doi.org/10.1162/coli_a_00446 |
spellingShingle | Barry Haddow Rachel Bawden Antonio Valerio Miceli Barone Jindřich Helcl Alexandra Birch Survey of Low-Resource Machine Translation Computational Linguistics |
title | Survey of Low-Resource Machine Translation |
title_full | Survey of Low-Resource Machine Translation |
title_fullStr | Survey of Low-Resource Machine Translation |
title_full_unstemmed | Survey of Low-Resource Machine Translation |
title_short | Survey of Low-Resource Machine Translation |
title_sort | survey of low resource machine translation |
url | http://dx.doi.org/10.1162/coli_a_00446 |
work_keys_str_mv | AT barryhaddow surveyoflowresourcemachinetranslation AT rachelbawden surveyoflowresourcemachinetranslation AT antoniovaleriomicelibarone surveyoflowresourcemachinetranslation AT jindrichhelcl surveyoflowresourcemachinetranslation AT alexandrabirch surveyoflowresourcemachinetranslation |