@inproceedings{doumbouya-etal-2023-machine,
title = "Machine Translation for Nko: Tools, Corpora, and Baseline Results",
author = "Doumbouya, Moussa and
Dian{\'e}, Baba Mamadi and
Ciss{\'e}, Solo Farabado and
Dian{\'e}, Djibrila and
Sow, Abdoulaye and
Doumbouya, S{\'e}r{\'e} Moussa and
Bangoura, Daouda and
Bayo, Fod{\'e} Moriba and
Conde, Ibrahima Sory and
Dian{\'e}, Kalo Mory and
Piech, Chris and
Manning, Christopher",
editor = "Koehn, Philipp and
Haddow, Barry and
Kocmi, Tom and
Monz, Christof",
booktitle = "Proceedings of the Eighth Conference on Machine Translation",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.wmt-1.34",
doi = "10.18653/v1/2023.wmt-1.34",
pages = "312--343",
abstract = "Currently, there is no usable machine translation system for Nko, a language spoken by tens of millions of people across multiple West African countries, which holds significant cultural and educational value. To address this issue, we present a set of tools, resources, and baseline results aimed towards the development of usable machine translation systems for Nko and other languages that do not currently have sufficiently large parallel text corpora available. (1) Fria$\parallel$el: A novel collaborative parallel text curation software that incorporates quality control through copyedit-based workflows. (2) Expansion of the FLoRes-200 and NLLB-Seed corpora with 2,009 and 6,193 high-quality Nko translations in parallel with 204 and 40 other languages. (3) nicolingua-0005: A collection of trilingual and bilingual corpora with 130,850 parallel segments and monolingual corpora containing over 3 million Nko words. (4) Baseline bilingual and multilingual neural machine translation results with the best model scoring 30.83 English-Nko chrF++ on FLoRes-devtest.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="doumbouya-etal-2023-machine">
<titleInfo>
<title>Machine Translation for Nko: Tools, Corpora, and Baseline Results</title>
</titleInfo>
<name type="personal">
<namePart type="given">Moussa</namePart>
<namePart type="family">Doumbouya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baba</namePart>
<namePart type="given">Mamadi</namePart>
<namePart type="family">Diané</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Solo</namePart>
<namePart type="given">Farabado</namePart>
<namePart type="family">Cissé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Djibrila</namePart>
<namePart type="family">Diané</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdoulaye</namePart>
<namePart type="family">Sow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Séré</namePart>
<namePart type="given">Moussa</namePart>
<namePart type="family">Doumbouya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daouda</namePart>
<namePart type="family">Bangoura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fodé</namePart>
<namePart type="given">Moriba</namePart>
<namePart type="family">Bayo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahima</namePart>
<namePart type="given">Sory</namePart>
<namePart type="family">Conde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalo</namePart>
<namePart type="given">Mory</namePart>
<namePart type="family">Diané</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Piech</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Manning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Currently, there is no usable machine translation system for Nko, a language spoken by tens of millions of people across multiple West African countries, which holds significant cultural and educational value. To address this issue, we present a set of tools, resources, and baseline results aimed towards the development of usable machine translation systems for Nko and other languages that do not currently have sufficiently large parallel text corpora available. (1) Fria\parallelel: A novel collaborative parallel text curation software that incorporates quality control through copyedit-based workflows. (2) Expansion of the FLoRes-200 and NLLB-Seed corpora with 2,009 and 6,193 high-quality Nko translations in parallel with 204 and 40 other languages. (3) nicolingua-0005: A collection of trilingual and bilingual corpora with 130,850 parallel segments and monolingual corpora containing over 3 million Nko words. (4) Baseline bilingual and multilingual neural machine translation results with the best model scoring 30.83 English-Nko chrF++ on FLoRes-devtest.</abstract>
<identifier type="citekey">doumbouya-etal-2023-machine</identifier>
<identifier type="doi">10.18653/v1/2023.wmt-1.34</identifier>
<location>
<url>https://aclanthology.org/2023.wmt-1.34</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>312</start>
<end>343</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Machine Translation for Nko: Tools, Corpora, and Baseline Results
%A Doumbouya, Moussa
%A Diané, Baba Mamadi
%A Cissé, Solo Farabado
%A Diané, Djibrila
%A Sow, Abdoulaye
%A Doumbouya, Séré Moussa
%A Bangoura, Daouda
%A Bayo, Fodé Moriba
%A Conde, Ibrahima Sory
%A Diané, Kalo Mory
%A Piech, Chris
%A Manning, Christopher
%Y Koehn, Philipp
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Monz, Christof
%S Proceedings of the Eighth Conference on Machine Translation
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F doumbouya-etal-2023-machine
%X Currently, there is no usable machine translation system for Nko, a language spoken by tens of millions of people across multiple West African countries, which holds significant cultural and educational value. To address this issue, we present a set of tools, resources, and baseline results aimed towards the development of usable machine translation systems for Nko and other languages that do not currently have sufficiently large parallel text corpora available. (1) Fria\parallelel: A novel collaborative parallel text curation software that incorporates quality control through copyedit-based workflows. (2) Expansion of the FLoRes-200 and NLLB-Seed corpora with 2,009 and 6,193 high-quality Nko translations in parallel with 204 and 40 other languages. (3) nicolingua-0005: A collection of trilingual and bilingual corpora with 130,850 parallel segments and monolingual corpora containing over 3 million Nko words. (4) Baseline bilingual and multilingual neural machine translation results with the best model scoring 30.83 English-Nko chrF++ on FLoRes-devtest.
%R 10.18653/v1/2023.wmt-1.34
%U https://aclanthology.org/2023.wmt-1.34
%U https://doi.org/10.18653/v1/2023.wmt-1.34
%P 312-343
Markdown (Informal)
[Machine Translation for Nko: Tools, Corpora, and Baseline Results](https://aclanthology.org/2023.wmt-1.34) (Doumbouya et al., WMT 2023)
ACL
- Moussa Doumbouya, Baba Mamadi Diané, Solo Farabado Cissé, Djibrila Diané, Abdoulaye Sow, Séré Moussa Doumbouya, Daouda Bangoura, Fodé Moriba Bayo, Ibrahima Sory Conde, Kalo Mory Diané, Chris Piech, and Christopher Manning. 2023. Machine Translation for Nko: Tools, Corpora, and Baseline Results. In Proceedings of the Eighth Conference on Machine Translation, pages 312–343, Singapore. Association for Computational Linguistics.