@inproceedings{perez-ortiz-2026-research,
title = "A Research Compass for the Acquisition of Thousands of Low-Resource Languages by {AI} Models via Form-Focused Study and Usage-Based Linguistic Immersion",
author = "P{\'e}rez-Ortiz, Juan Antonio",
editor = "Adelani, David Ifeoluwa and
Alabi, Jesujoba and
Arnett, Catherine and
Chang, Tyler and
Downey, C.M. and
Goldman, Omer and
Li, Senyu and
Miranda, Lester James Validad and
Qi, Jirui and
Stap, David and
Winata, Genta Indra and
Zhang, Xinyu Crystina",
booktitle = "Proceedings of the 6th Workshop on Multilingual Representation Learning ({MRL} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mrl-1.50/",
pages = "665--683",
ISBN = "979-8-89176-469-9",
abstract = "This position paper provides a multifaceted perspective on the challenge of adapting AI models (notably, large language models, LLMs) to the thousands of languages spoken worldwide which lack the vast amounts of text necessary for conventional data-intensive, imitation-based training. The paper explores two complementary emerging learning paths which are currently underexplored in the literature: explicit instruction-guided learning from linguistic resources and implicit acquisition in natural immersion contexts. By synthesizing current advances and identifying 40 open problems, this study defines an interdisciplinary research compass for the coming years."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="perez-ortiz-2026-research">
<titleInfo>
<title>A Research Compass for the Acquisition of Thousands of Low-Resource Languages by AI Models via Form-Focused Study and Usage-Based Linguistic Immersion</title>
</titleInfo>
<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>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Downey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Goldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lester</namePart>
<namePart type="given">James</namePart>
<namePart type="given">Validad</namePart>
<namePart type="family">Miranda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jirui</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="given">Crystina</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-469-9</identifier>
</relatedItem>
<abstract>This position paper provides a multifaceted perspective on the challenge of adapting AI models (notably, large language models, LLMs) to the thousands of languages spoken worldwide which lack the vast amounts of text necessary for conventional data-intensive, imitation-based training. The paper explores two complementary emerging learning paths which are currently underexplored in the literature: explicit instruction-guided learning from linguistic resources and implicit acquisition in natural immersion contexts. By synthesizing current advances and identifying 40 open problems, this study defines an interdisciplinary research compass for the coming years.</abstract>
<identifier type="citekey">perez-ortiz-2026-research</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.50/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>665</start>
<end>683</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Research Compass for the Acquisition of Thousands of Low-Resource Languages by AI Models via Form-Focused Study and Usage-Based Linguistic Immersion
%A Pérez-Ortiz, Juan Antonio
%Y Adelani, David Ifeoluwa
%Y Alabi, Jesujoba
%Y Arnett, Catherine
%Y Chang, Tyler
%Y Downey, C. M.
%Y Goldman, Omer
%Y Li, Senyu
%Y Miranda, Lester James Validad
%Y Qi, Jirui
%Y Stap, David
%Y Winata, Genta Indra
%Y Zhang, Xinyu Crystina
%S Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-469-9
%F perez-ortiz-2026-research
%X This position paper provides a multifaceted perspective on the challenge of adapting AI models (notably, large language models, LLMs) to the thousands of languages spoken worldwide which lack the vast amounts of text necessary for conventional data-intensive, imitation-based training. The paper explores two complementary emerging learning paths which are currently underexplored in the literature: explicit instruction-guided learning from linguistic resources and implicit acquisition in natural immersion contexts. By synthesizing current advances and identifying 40 open problems, this study defines an interdisciplinary research compass for the coming years.
%U https://aclanthology.org/2026.mrl-1.50/
%P 665-683
Markdown (Informal)
[A Research Compass for the Acquisition of Thousands of Low-Resource Languages by AI Models via Form-Focused Study and Usage-Based Linguistic Immersion](https://aclanthology.org/2026.mrl-1.50/) (Pérez-Ortiz, MRL 2026)
ACL