@inproceedings{ramirez-vidal-etal-2026-llm,
title = "{LLM}-Assisted {S}panish Dialect Corpus Construction",
author = "RAMIREZ VIDAL, Jessica Claribel and
Ouchi, Hiroki and
Sakti, Sakriani",
editor = "Ojha, Atul Kr. and
Sakti, Sakriani and
Soria, Claudia and
Melero, Maite and
McCrae, John P. and
Lignos, Constantine and
Liu, Chao-Hong and
Claramunt, German Rigau and
Rehm, Georg",
booktitle = "Proceedings of the {SIGUL} 2026 Joint Workshop with {ELE}, {EURALI}, and {DCLRL}: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages",
month = may,
year = "2026",
address = "Palma, Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.sigul-1.16/",
doi = "10.63317/3zod9jyperib",
pages = "153--159",
abstract = "This study presents a multi-dialect, pragmatically annotated Spanish corpus designed to address persistent gaps in the representation of regional varieties and communicative functions in existing linguistic and NLP resources. The corpus focuses exclusively on Spanish dialects spoken in the Americas, selecting one representative dialect per country and incorporating a single neutral Castilian variety for comparative purposes. Dialects are organized into five regional groups: Mexican, Central American, Caribbean, South American, and Rioplatense Spanish. Corpus development follows a multi-stage workflow in which a seed lexicon composed of openly licensed material from sources such as Wikipedia, Project Gutenberg, and curated random and synthetic data is used to initiate the LLM-based text generation. Each base sentence is expanded into dialect-specific variants and annotated with pragmatic and domain labels, producing a fully parallel dataset that supports cross dialect comparison. A multi-stage correction pipeline combining automated scripts, controlled LLM-based editing, and manual review ensures syntactic well-formedness and dialectal authenticity while eliminating language-switching and hallucination errors. The final version of the corpus covers 20 dialects and contains, 40,000 annotated sentences, released in both JSON and plain-text formats for use in a wide range of NLP tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ramirez-vidal-etal-2026-llm">
<titleInfo>
<title>LLM-Assisted Spanish Dialect Corpus Construction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jessica</namePart>
<namePart type="given">Claribel</namePart>
<namePart type="family">RAMIREZ VIDAL</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Ouchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</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 SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="given">Rigau</namePart>
<namePart type="family">Claramunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study presents a multi-dialect, pragmatically annotated Spanish corpus designed to address persistent gaps in the representation of regional varieties and communicative functions in existing linguistic and NLP resources. The corpus focuses exclusively on Spanish dialects spoken in the Americas, selecting one representative dialect per country and incorporating a single neutral Castilian variety for comparative purposes. Dialects are organized into five regional groups: Mexican, Central American, Caribbean, South American, and Rioplatense Spanish. Corpus development follows a multi-stage workflow in which a seed lexicon composed of openly licensed material from sources such as Wikipedia, Project Gutenberg, and curated random and synthetic data is used to initiate the LLM-based text generation. Each base sentence is expanded into dialect-specific variants and annotated with pragmatic and domain labels, producing a fully parallel dataset that supports cross dialect comparison. A multi-stage correction pipeline combining automated scripts, controlled LLM-based editing, and manual review ensures syntactic well-formedness and dialectal authenticity while eliminating language-switching and hallucination errors. The final version of the corpus covers 20 dialects and contains, 40,000 annotated sentences, released in both JSON and plain-text formats for use in a wide range of NLP tasks.</abstract>
<identifier type="citekey">ramirez-vidal-etal-2026-llm</identifier>
<identifier type="doi">10.63317/3zod9jyperib</identifier>
<location>
<url>https://aclanthology.org/2026.sigul-1.16/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>153</start>
<end>159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM-Assisted Spanish Dialect Corpus Construction
%A RAMIREZ VIDAL, Jessica Claribel
%A Ouchi, Hiroki
%A Sakti, Sakriani
%Y Ojha, Atul Kr.
%Y Sakti, Sakriani
%Y Soria, Claudia
%Y Melero, Maite
%Y McCrae, John P.
%Y Lignos, Constantine
%Y Liu, Chao-Hong
%Y Claramunt, German Rigau
%Y Rehm, Georg
%S Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca, Spain
%F ramirez-vidal-etal-2026-llm
%X This study presents a multi-dialect, pragmatically annotated Spanish corpus designed to address persistent gaps in the representation of regional varieties and communicative functions in existing linguistic and NLP resources. The corpus focuses exclusively on Spanish dialects spoken in the Americas, selecting one representative dialect per country and incorporating a single neutral Castilian variety for comparative purposes. Dialects are organized into five regional groups: Mexican, Central American, Caribbean, South American, and Rioplatense Spanish. Corpus development follows a multi-stage workflow in which a seed lexicon composed of openly licensed material from sources such as Wikipedia, Project Gutenberg, and curated random and synthetic data is used to initiate the LLM-based text generation. Each base sentence is expanded into dialect-specific variants and annotated with pragmatic and domain labels, producing a fully parallel dataset that supports cross dialect comparison. A multi-stage correction pipeline combining automated scripts, controlled LLM-based editing, and manual review ensures syntactic well-formedness and dialectal authenticity while eliminating language-switching and hallucination errors. The final version of the corpus covers 20 dialects and contains, 40,000 annotated sentences, released in both JSON and plain-text formats for use in a wide range of NLP tasks.
%R 10.63317/3zod9jyperib
%U https://aclanthology.org/2026.sigul-1.16/
%U https://doi.org/10.63317/3zod9jyperib
%P 153-159
Markdown (Informal)
[LLM-Assisted Spanish Dialect Corpus Construction](https://aclanthology.org/2026.sigul-1.16/) (RAMIREZ VIDAL et al., SIGUL-EURALI-DCLRL 2026)
ACL
- Jessica Claribel RAMIREZ VIDAL, Hiroki Ouchi, and Sakriani Sakti. 2026. LLM-Assisted Spanish Dialect Corpus Construction. In Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages, pages 153–159, Palma, Mallorca, Spain. ELRA Language Resources Association (ELRA).