@inproceedings{guzman-landa-etal-2025-p,
title = "{\ensuremath{\pi}}-{YALLI} : un nouveau corpus pour des mod{\`e}les de langue nahuatl / Yankuik nawatlahtolkorpus pampa tlahtolmachiotl",
author = "Guzm{\'a}n-Landa, Juan-Jos{\'e} and
Torres-Moreno, Juan-Manuel and
Lorena Avenda{\~n}o Garrido, Martha and
Figueroa-Saavedra, Miguel and
Quintana-Torres, Ligia and
Ranger, Graham and
Gonz{\'a}lez-Gallardo, Carlos-Emiliano and
Linhares-Pontes, Elvys and
Vel{\'a}zquez-Morales, Patricia and
Moreno-Jim{\'e}nez, Luis-Gil",
editor = "Bechet, Fr{\'e}d{\'e}ric and
Chifu, Adrian-Gabriel and
Pinel-sauvagnat, Karen and
Favre, Benoit and
Maes, Eliot and
Nurbakova, Diana",
booktitle = "Actes des 32{\`e}me Conf{\'e}rence sur le Traitement Automatique des Langues Naturelles (TALN), volume 1 : articles scientifiques originaux",
month = "6",
year = "2025",
address = "Marseille, France",
publisher = "ATALA {\textbackslash}{\textbackslash}{\&} ARIA",
url = "https://aclanthology.org/2025.jeptalnrecital-taln.49/",
pages = "802--816",
abstract = "{\ensuremath{\pi}}-YALLI : a new corpus for Nahuatl Language Models The Nahuatl is a language with few computational resources, despite the fact that it is a living language spoken by around two million people. We built {\ensuremath{\pi}}-YALLI, a corpus that enables research and development of dynamic and static Language Models (LM). We measured the perplexity of {\ensuremath{\pi}}-YALLI, evaluating state-of-the-art LM performance on a manually annotated semantic similarity corpus relative to annotator agreement. The results show the difficulty of working with this {\ensuremath{\pi}}-language, but at the same time open up interesting perspectives for the study of other NLP tasks on Nahuatl."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guzman-landa-etal-2025-p">
<titleInfo>
<title>\ensuremathπ-YALLI : un nouveau corpus pour des modèles de langue nahuatl / Yankuik nawatlahtolkorpus pampa tlahtolmachiotl</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juan-José</namePart>
<namePart type="family">Guzmán-Landa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan-Manuel</namePart>
<namePart type="family">Torres-Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="family">Lorena Avendaño Garrido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Figueroa-Saavedra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ligia</namePart>
<namePart type="family">Quintana-Torres</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Ranger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos-Emiliano</namePart>
<namePart type="family">González-Gallardo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elvys</namePart>
<namePart type="family">Linhares-Pontes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patricia</namePart>
<namePart type="family">Velázquez-Morales</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis-Gil</namePart>
<namePart type="family">Moreno-Jiménez</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>Actes des 32ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 1 : articles scientifiques originaux</title>
</titleInfo>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Bechet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian-Gabriel</namePart>
<namePart type="family">Chifu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Pinel-sauvagnat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoit</namePart>
<namePart type="family">Favre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eliot</namePart>
<namePart type="family">Maes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Nurbakova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ATALA \textbackslash\textbackslash& ARIA</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>\ensuremathπ-YALLI : a new corpus for Nahuatl Language Models The Nahuatl is a language with few computational resources, despite the fact that it is a living language spoken by around two million people. We built \ensuremathπ-YALLI, a corpus that enables research and development of dynamic and static Language Models (LM). We measured the perplexity of \ensuremathπ-YALLI, evaluating state-of-the-art LM performance on a manually annotated semantic similarity corpus relative to annotator agreement. The results show the difficulty of working with this \ensuremathπ-language, but at the same time open up interesting perspectives for the study of other NLP tasks on Nahuatl.</abstract>
<identifier type="citekey">guzman-landa-etal-2025-p</identifier>
<location>
<url>https://aclanthology.org/2025.jeptalnrecital-taln.49/</url>
</location>
<part>
<date>2025-6</date>
<extent unit="page">
<start>802</start>
<end>816</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T \ensuremathπ-YALLI : un nouveau corpus pour des modèles de langue nahuatl / Yankuik nawatlahtolkorpus pampa tlahtolmachiotl
%A Guzmán-Landa, Juan-José
%A Torres-Moreno, Juan-Manuel
%A Lorena Avendaño Garrido, Martha
%A Figueroa-Saavedra, Miguel
%A Quintana-Torres, Ligia
%A Ranger, Graham
%A González-Gallardo, Carlos-Emiliano
%A Linhares-Pontes, Elvys
%A Velázquez-Morales, Patricia
%A Moreno-Jiménez, Luis-Gil
%Y Bechet, Frédéric
%Y Chifu, Adrian-Gabriel
%Y Pinel-sauvagnat, Karen
%Y Favre, Benoit
%Y Maes, Eliot
%Y Nurbakova, Diana
%S Actes des 32ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 1 : articles scientifiques originaux
%D 2025
%8 June
%I ATALA \textbackslash\textbackslash& ARIA
%C Marseille, France
%F guzman-landa-etal-2025-p
%X \ensuremathπ-YALLI : a new corpus for Nahuatl Language Models The Nahuatl is a language with few computational resources, despite the fact that it is a living language spoken by around two million people. We built \ensuremathπ-YALLI, a corpus that enables research and development of dynamic and static Language Models (LM). We measured the perplexity of \ensuremathπ-YALLI, evaluating state-of-the-art LM performance on a manually annotated semantic similarity corpus relative to annotator agreement. The results show the difficulty of working with this \ensuremathπ-language, but at the same time open up interesting perspectives for the study of other NLP tasks on Nahuatl.
%U https://aclanthology.org/2025.jeptalnrecital-taln.49/
%P 802-816
Markdown (Informal)
[π-YALLI : un nouveau corpus pour des modèles de langue nahuatl / Yankuik nawatlahtolkorpus pampa tlahtolmachiotl](https://aclanthology.org/2025.jeptalnrecital-taln.49/) (Guzmán-Landa et al., JEP/TALN/RECITAL 2025)
ACL
- Juan-José Guzmán-Landa, Juan-Manuel Torres-Moreno, Martha Lorena Avendaño Garrido, Miguel Figueroa-Saavedra, Ligia Quintana-Torres, Graham Ranger, Carlos-Emiliano González-Gallardo, Elvys Linhares-Pontes, Patricia Velázquez-Morales, and Luis-Gil Moreno-Jiménez. 2025. π-YALLI : un nouveau corpus pour des modèles de langue nahuatl / Yankuik nawatlahtolkorpus pampa tlahtolmachiotl. In Actes des 32ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 1 : articles scientifiques originaux, pages 802–816, Marseille, France. ATALA \\& ARIA.