Survey of Low-Resource Machine Translation

Barry Haddow; Rachel Bawden; Antonio Valerio Miceli Barone; Jindřich Helcl; Alexandra Birch

doi:10.1162/coli_a_00446

Survey of Low-Resource Machine Translation

Barry Haddow, Rachel Bawden, Antonio Valerio Miceli Barone, Jindřich Helcl, Alexandra Birch

Research output: Contribution to journal › Article › peer-review

Abstract / Description of output

We present a survey covering the state of the art in low-resource machine translation research. There are currently around 7000 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.

Original language	English
Pages (from-to)	673-732
Number of pages	67
Journal	Computational Linguistics
Volume	48
Issue number	3
DOIs	https://doi.org/10.1162/coli_a_00446
Publication status	Published - 1 Sept 2022

Access to Document

10.1162/coli_a_00446Licence: Creative Commons: Attribution-NonCommercial-NoDerivatives (CC BY-NC-ND)

Survey_of_Low_HADDOW_DOA21022022_VOR_CC_BY_NC_NDFinal published version, 563 KBLicence: Creative Commons: Attribution-NonCommercial-NoDerivatives (CC BY-NC-ND)

https://direct.mit.edu/coli/article/doi/10.1162/coli_a_00446/111479/Survey-of-Low-Resource-Machine-TranslationLicence: Creative Commons: Attribution-NonCommercial-NoDerivatives (CC BY-NC-ND)

Global Under-Resourced MEdia Translation
Birch-Mayne, A. & Haddow, B.
EU government bodies
1/01/19 → 30/06/22
Project: Research
MTStretch: Low-resource Machine Translation
Birch-Mayne, A.
EPSRC
29/06/18 → 28/12/21
Project: Research

Cite this

@article{b55318bdbe684f0e871f4fe7f328ef48,

title = "Survey of Low-Resource Machine Translation",

abstract = "We present a survey covering the state of the art in low-resource machine translation research. There are currently around 7000 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.",

author = "Barry Haddow and Rachel Bawden and {Miceli Barone}, {Antonio Valerio} and Jind{\v r}ich Helcl and Alexandra Birch",

note = "Funding Information: This work was partly funded by Rachel Bawden{\textquoteright}s chair in the PRAIRIE institute funded by the French national agency ANR as part of the “Investissements d{\textquoteright}avenir” programme under the reference ANR-19-P3IA-0001. This work has received funding from the European Union{\textquoteright}s Horizon 2020 Research and Innovation Programme under Grant Agreement No. 825299 (GoURMET). It was also supported by the UK Engineering and Physical Sciences Research Council fellowship grant EP/S001271/1 (MTStretch). Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.",

year = "2022",

month = sep,

day = "1",

doi = "10.1162/coli_a_00446",

language = "English",

volume = "48",

pages = "673--732",

journal = "Computational Linguistics",

issn = "0891-2017",

publisher = "MIT Press Journals",

number = "3",

}

TY - JOUR

T1 - Survey of Low-Resource Machine Translation

AU - Haddow, Barry

AU - Bawden, Rachel

AU - Miceli Barone, Antonio Valerio

AU - Helcl, Jindřich

AU - Birch, Alexandra

N1 - Funding Information: This work was partly funded by Rachel Bawden’s chair in the PRAIRIE institute funded by the French national agency ANR as part of the “Investissements d’avenir” programme under the reference ANR-19-P3IA-0001. This work has received funding from the European Union’s Horizon 2020 Research and Innovation Programme under Grant Agreement No. 825299 (GoURMET). It was also supported by the UK Engineering and Physical Sciences Research Council fellowship grant EP/S001271/1 (MTStretch). Publisher Copyright: © 2022 Association for Computational Linguistics.

PY - 2022/9/1

Y1 - 2022/9/1

N2 - We present a survey covering the state of the art in low-resource machine translation research. There are currently around 7000 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.

AB - We present a survey covering the state of the art in low-resource machine translation research. There are currently around 7000 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.

U2 - 10.1162/coli_a_00446

DO - 10.1162/coli_a_00446

M3 - Article

SN - 0891-2017

VL - 48

SP - 673

EP - 732

JO - Computational Linguistics

JF - Computational Linguistics

IS - 3

ER -

Survey of Low-Resource Machine Translation

Abstract / Description of output

Access to Document

Fingerprint

Projects

Global Under-Resourced MEdia Translation

MTStretch: Low-resource Machine Translation

Cite this