@inproceedings{robinson-etal-2024-kreyol,
title = "Krey{\`o}l-{MT}: Building {MT} for {L}atin {A}merican, {C}aribbean and Colonial {A}frican Creole Languages",
author = {Robinson, Nathaniel R. and
Dabre, Raj and
Shurtz, Ammon and
Dent, Rasul and
Onesi, Onenamiyi and
Bizon Monroc, Claire and
Grobol, Lo{\"i}c and
Muhammad, Hasan and
Garg, Ashi and
Etori, Naome A. and
Tiyyala, Vijay Murari and
Samuel, Olanrewaju and
Stutzman, Matthew Dean and
Bamfo Odoom, Bismarck and
Khudanpur, Sanjeev and
Richardson, Stephen D. and
Murray, Kenton},
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.170/",
doi = "10.18653/v1/2024.naacl-long.170",
pages = "3083--3110",
abstract = "A majority of language technologies are tailored for a small number of high-resource languages, while relatively many low-resource languages are neglected. One such group, Creole languages, have long been marginalized in academic study, though their speakers could benefit from machine translation (MT). These languages are predominantly used in much of Latin America, Africa and the Caribbean. We present the largest cumulative dataset to date for Creole language MT, including 14.5M unique Creole sentences with parallel translations{---}11.6M of which we release publicly, and the largest bitexts gathered to date for 41 languages{---}the first ever for 21. In addition, we provide MT models supporting all 41 Creole languages in 172 translation directions. Given our diverse dataset, we produce a model for Creole language MT exposed to more genre diversity then ever before, which outperforms a genre-specific Creole MT model on its own benchmark for 23 of 34 translation directions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="robinson-etal-2024-kreyol">
<titleInfo>
<title>Kreyòl-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Robinson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ammon</namePart>
<namePart type="family">Shurtz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rasul</namePart>
<namePart type="family">Dent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Onenamiyi</namePart>
<namePart type="family">Onesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Bizon Monroc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Loïc</namePart>
<namePart type="family">Grobol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hasan</namePart>
<namePart type="family">Muhammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashi</namePart>
<namePart type="family">Garg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naome</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Etori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vijay</namePart>
<namePart type="given">Murari</namePart>
<namePart type="family">Tiyyala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olanrewaju</namePart>
<namePart type="family">Samuel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="given">Dean</namePart>
<namePart type="family">Stutzman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bismarck</namePart>
<namePart type="family">Bamfo Odoom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjeev</namePart>
<namePart type="family">Khudanpur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Richardson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenton</namePart>
<namePart type="family">Murray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A majority of language technologies are tailored for a small number of high-resource languages, while relatively many low-resource languages are neglected. One such group, Creole languages, have long been marginalized in academic study, though their speakers could benefit from machine translation (MT). These languages are predominantly used in much of Latin America, Africa and the Caribbean. We present the largest cumulative dataset to date for Creole language MT, including 14.5M unique Creole sentences with parallel translations—11.6M of which we release publicly, and the largest bitexts gathered to date for 41 languages—the first ever for 21. In addition, we provide MT models supporting all 41 Creole languages in 172 translation directions. Given our diverse dataset, we produce a model for Creole language MT exposed to more genre diversity then ever before, which outperforms a genre-specific Creole MT model on its own benchmark for 23 of 34 translation directions.</abstract>
<identifier type="citekey">robinson-etal-2024-kreyol</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.170</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.170/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>3083</start>
<end>3110</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Kreyòl-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages
%A Robinson, Nathaniel R.
%A Dabre, Raj
%A Shurtz, Ammon
%A Dent, Rasul
%A Onesi, Onenamiyi
%A Bizon Monroc, Claire
%A Grobol, Loïc
%A Muhammad, Hasan
%A Garg, Ashi
%A Etori, Naome A.
%A Tiyyala, Vijay Murari
%A Samuel, Olanrewaju
%A Stutzman, Matthew Dean
%A Bamfo Odoom, Bismarck
%A Khudanpur, Sanjeev
%A Richardson, Stephen D.
%A Murray, Kenton
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F robinson-etal-2024-kreyol
%X A majority of language technologies are tailored for a small number of high-resource languages, while relatively many low-resource languages are neglected. One such group, Creole languages, have long been marginalized in academic study, though their speakers could benefit from machine translation (MT). These languages are predominantly used in much of Latin America, Africa and the Caribbean. We present the largest cumulative dataset to date for Creole language MT, including 14.5M unique Creole sentences with parallel translations—11.6M of which we release publicly, and the largest bitexts gathered to date for 41 languages—the first ever for 21. In addition, we provide MT models supporting all 41 Creole languages in 172 translation directions. Given our diverse dataset, we produce a model for Creole language MT exposed to more genre diversity then ever before, which outperforms a genre-specific Creole MT model on its own benchmark for 23 of 34 translation directions.
%R 10.18653/v1/2024.naacl-long.170
%U https://aclanthology.org/2024.naacl-long.170/
%U https://doi.org/10.18653/v1/2024.naacl-long.170
%P 3083-3110
Markdown (Informal)
[Kreyòl-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages](https://aclanthology.org/2024.naacl-long.170/) (Robinson et al., NAACL 2024)
ACL
- Nathaniel R. Robinson, Raj Dabre, Ammon Shurtz, Rasul Dent, Onenamiyi Onesi, Claire Bizon Monroc, Loïc Grobol, Hasan Muhammad, Ashi Garg, Naome A. Etori, Vijay Murari Tiyyala, Olanrewaju Samuel, Matthew Dean Stutzman, Bismarck Bamfo Odoom, Sanjeev Khudanpur, Stephen D. Richardson, and Kenton Murray. 2024. Kreyòl-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 3083–3110, Mexico City, Mexico. Association for Computational Linguistics.