@inproceedings{guzman-landa-etal-2026-nawatl,
title = "Nawatl Context-Free Grammars for Natural Language Processing",
author = "Guzman Landa, Juan Jose and
Torres-Moreno, Juan-Manuel and
Ranger, Graham and
Figueroa-Saavedra, Miguel and
Quintana Torres, Ligia and
Gonzalez-Gallardo, Carlos-Emiliano and
Moreno Jimenez, Luis Gil and
Lorena Avenda{\~n}o Garrido, Martha",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.263/",
doi = "10.63317/5e2etyunwu7g",
pages = "3333--3342",
abstract = "The aim of this article is to introduce Context-Free Grammars (CFG) for the Nawatl language. Nawatl is an Amerindian language of the $\pi$-language type, i.e. a language with few digital resources. For this reason the corpora available for the learning of Large Language Models (LLMs) are virtually non-existent, posing a significant challenge. The goal is to produce a substantial number of syntactically valid artificial Nawatl sentences and thereby to expand the corpora for the purpose of learning embeddings (static models or probably LLMs). For this objective, we introduce two new Nawatl CFGs and use them in generative mode. Thanks to these grammars, it is possible to expand Nawatl corpus significantly and subsequently to use it to learn embeddings (such as FastText) and to evaluate their relevance in semantic similarity tasks. The results show an improvement compared to the results obtained using only the original corpus without artificial expansion, and also demonstrate that economic embeddings often perform better than some LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guzman-landa-etal-2026-nawatl">
<titleInfo>
<title>Nawatl Context-Free Grammars for Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Jose</namePart>
<namePart type="family">Guzman 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">Graham</namePart>
<namePart type="family">Ranger</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">Carlos-Emiliano</namePart>
<namePart type="family">Gonzalez-Gallardo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="given">Gil</namePart>
<namePart type="family">Moreno Jimenez</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>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The aim of this article is to introduce Context-Free Grammars (CFG) for the Nawatl language. Nawatl is an Amerindian language of the π-language type, i.e. a language with few digital resources. For this reason the corpora available for the learning of Large Language Models (LLMs) are virtually non-existent, posing a significant challenge. The goal is to produce a substantial number of syntactically valid artificial Nawatl sentences and thereby to expand the corpora for the purpose of learning embeddings (static models or probably LLMs). For this objective, we introduce two new Nawatl CFGs and use them in generative mode. Thanks to these grammars, it is possible to expand Nawatl corpus significantly and subsequently to use it to learn embeddings (such as FastText) and to evaluate their relevance in semantic similarity tasks. The results show an improvement compared to the results obtained using only the original corpus without artificial expansion, and also demonstrate that economic embeddings often perform better than some LLMs.</abstract>
<identifier type="citekey">guzman-landa-etal-2026-nawatl</identifier>
<identifier type="doi">10.63317/5e2etyunwu7g</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.263/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>3333</start>
<end>3342</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Nawatl Context-Free Grammars for Natural Language Processing
%A Guzman Landa, Juan Jose
%A Torres-Moreno, Juan-Manuel
%A Ranger, Graham
%A Figueroa-Saavedra, Miguel
%A Quintana Torres, Ligia
%A Gonzalez-Gallardo, Carlos-Emiliano
%A Moreno Jimenez, Luis Gil
%A Lorena Avendaño Garrido, Martha
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F guzman-landa-etal-2026-nawatl
%X The aim of this article is to introduce Context-Free Grammars (CFG) for the Nawatl language. Nawatl is an Amerindian language of the π-language type, i.e. a language with few digital resources. For this reason the corpora available for the learning of Large Language Models (LLMs) are virtually non-existent, posing a significant challenge. The goal is to produce a substantial number of syntactically valid artificial Nawatl sentences and thereby to expand the corpora for the purpose of learning embeddings (static models or probably LLMs). For this objective, we introduce two new Nawatl CFGs and use them in generative mode. Thanks to these grammars, it is possible to expand Nawatl corpus significantly and subsequently to use it to learn embeddings (such as FastText) and to evaluate their relevance in semantic similarity tasks. The results show an improvement compared to the results obtained using only the original corpus without artificial expansion, and also demonstrate that economic embeddings often perform better than some LLMs.
%R 10.63317/5e2etyunwu7g
%U https://aclanthology.org/2026.lrec-1.263/
%U https://doi.org/10.63317/5e2etyunwu7g
%P 3333-3342
Markdown (Informal)
[Nawatl Context-Free Grammars for Natural Language Processing](https://aclanthology.org/2026.lrec-1.263/) (Guzman Landa et al., LREC 2026)
ACL
- Juan Jose Guzman Landa, Juan-Manuel Torres-Moreno, Graham Ranger, Miguel Figueroa-Saavedra, Ligia Quintana Torres, Carlos-Emiliano Gonzalez-Gallardo, Luis Gil Moreno Jimenez, and Martha Lorena Avendaño Garrido. 2026. Nawatl Context-Free Grammars for Natural Language Processing. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 3333–3342, Palma de Mallorca, Spain. ELRA Language Resource Association.