@inproceedings{lou-etal-2025-flores,
title = "{FLORES}+ Mayas: Generating Textual Resources to Foster the Development of Language Technologies for {M}ayan Languages",
author = "Lou, Andr{\'e}s and
P{\'e}rez-Ortiz, Juan Antonio and
S{\'a}nchez-Mart{\'i}nez, Felipe and
Espl{\`a}-Gomis, Miquel and
S{\'a}nchez-Cartagena, V{\'i}ctor M.",
editor = {Bouillon, Pierrette and
Gerlach, Johanna and
Girletti, Sabrina and
Volkart, Lise and
Rubino, Raphael and
Sennrich, Rico and
L{\"a}ubli, Samuel and
Volk, Martin and
Espl{\`a}-Gomis, Miquel and
Vandeghinste, Vincent and
Moniz, Helena and
Szoc, Sara},
booktitle = "Proceedings of Machine Translation Summit XX: Volume 2",
month = jun,
year = "2025",
address = "Geneva, Switzerland",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2025.mtsummit-2.15/",
pages = "89--90",
ISBN = "978-2-9701897-1-8",
abstract = {A significant percentage of the population of Guatemala and Mexico belongs to various Mayan indigenous communities, for whom language barriers lead to social, economic, and digital exclusion. The Mayan languages spoken by these communities remain severely underrepresented in terms of digital resources, which prevents them from leveraging the latest advances in artificial intelligence. This project addresses that problem by means of: 1) the digitisation and release of multiple printed linguistic resources; 2) the development of a high-quality parallel machine translation (MT) evaluation corpus for six Mayan languages. In doing so, we are paving the way for the development of MT systems that will facilitate the access for Mayan speakers to essential services such as healthcare or legal aid. The resources are produced with the essential participation of indigenous communities, whereby native speakers provide the necessary translation services, QA, and linguistic expertise. The project is funded by the Google Academic Research Awards and carried out in collaboration with the Proyecto Ling{\"u}{\'i}stico Francisco Marroqu{\'i}n Foundation in Guatemala.}
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lou-etal-2025-flores">
<titleInfo>
<title>FLORES+ Mayas: Generating Textual Resources to Foster the Development of Language Technologies for Mayan Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrés</namePart>
<namePart type="family">Lou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Antonio</namePart>
<namePart type="family">Pérez-Ortiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felipe</namePart>
<namePart type="family">Sánchez-Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miquel</namePart>
<namePart type="family">Esplà-Gomis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Víctor</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Sánchez-Cartagena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit XX: Volume 2</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pierrette</namePart>
<namePart type="family">Bouillon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Gerlach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabrina</namePart>
<namePart type="family">Girletti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lise</namePart>
<namePart type="family">Volkart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raphael</namePart>
<namePart type="family">Rubino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rico</namePart>
<namePart type="family">Sennrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Läubli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Volk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miquel</namePart>
<namePart type="family">Esplà-Gomis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Vandeghinste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Szoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Geneva, Switzerland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-2-9701897-1-8</identifier>
</relatedItem>
<abstract>A significant percentage of the population of Guatemala and Mexico belongs to various Mayan indigenous communities, for whom language barriers lead to social, economic, and digital exclusion. The Mayan languages spoken by these communities remain severely underrepresented in terms of digital resources, which prevents them from leveraging the latest advances in artificial intelligence. This project addresses that problem by means of: 1) the digitisation and release of multiple printed linguistic resources; 2) the development of a high-quality parallel machine translation (MT) evaluation corpus for six Mayan languages. In doing so, we are paving the way for the development of MT systems that will facilitate the access for Mayan speakers to essential services such as healthcare or legal aid. The resources are produced with the essential participation of indigenous communities, whereby native speakers provide the necessary translation services, QA, and linguistic expertise. The project is funded by the Google Academic Research Awards and carried out in collaboration with the Proyecto Lingüístico Francisco Marroquín Foundation in Guatemala.</abstract>
<identifier type="citekey">lou-etal-2025-flores</identifier>
<location>
<url>https://aclanthology.org/2025.mtsummit-2.15/</url>
</location>
<part>
<date>2025-06</date>
<extent unit="page">
<start>89</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FLORES+ Mayas: Generating Textual Resources to Foster the Development of Language Technologies for Mayan Languages
%A Lou, Andrés
%A Pérez-Ortiz, Juan Antonio
%A Sánchez-Martínez, Felipe
%A Esplà-Gomis, Miquel
%A Sánchez-Cartagena, Víctor M.
%Y Bouillon, Pierrette
%Y Gerlach, Johanna
%Y Girletti, Sabrina
%Y Volkart, Lise
%Y Rubino, Raphael
%Y Sennrich, Rico
%Y Läubli, Samuel
%Y Volk, Martin
%Y Esplà-Gomis, Miquel
%Y Vandeghinste, Vincent
%Y Moniz, Helena
%Y Szoc, Sara
%S Proceedings of Machine Translation Summit XX: Volume 2
%D 2025
%8 June
%I European Association for Machine Translation
%C Geneva, Switzerland
%@ 978-2-9701897-1-8
%F lou-etal-2025-flores
%X A significant percentage of the population of Guatemala and Mexico belongs to various Mayan indigenous communities, for whom language barriers lead to social, economic, and digital exclusion. The Mayan languages spoken by these communities remain severely underrepresented in terms of digital resources, which prevents them from leveraging the latest advances in artificial intelligence. This project addresses that problem by means of: 1) the digitisation and release of multiple printed linguistic resources; 2) the development of a high-quality parallel machine translation (MT) evaluation corpus for six Mayan languages. In doing so, we are paving the way for the development of MT systems that will facilitate the access for Mayan speakers to essential services such as healthcare or legal aid. The resources are produced with the essential participation of indigenous communities, whereby native speakers provide the necessary translation services, QA, and linguistic expertise. The project is funded by the Google Academic Research Awards and carried out in collaboration with the Proyecto Lingüístico Francisco Marroquín Foundation in Guatemala.
%U https://aclanthology.org/2025.mtsummit-2.15/
%P 89-90
Markdown (Informal)
[FLORES+ Mayas: Generating Textual Resources to Foster the Development of Language Technologies for Mayan Languages](https://aclanthology.org/2025.mtsummit-2.15/) (Lou et al., MTSummit 2025)
ACL