@inproceedings{garcia-cerda-etal-2025-building,
title = "Building a Lightweight Classifier to Distinguish Closely Related Language Varieties with Limited Supervision: The Case of {C}atalan vs {V}alencian",
author = "Garc{\'i}a Cerd{\'a}, Ra{\'u}l and
Mir{\'o} Maestre, Mar{\'i}a and
Canal, Miquel",
editor = "Estevanell-Valladares, Ernesto Luis and
Picazo-Izquierdo, Alicia and
Ranasinghe, Tharindu and
Mikaberidze, Besik and
Ostermann, Simon and
Gurgurov, Daniil and
Mueller, Philipp and
Borg, Claudia and
{\v{S}}imko, Mari{\'a}n",
booktitle = "Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.lowresnlp-1.2/",
pages = "7--11",
abstract = "Dialectal variation among closely related languages poses a major challenge in low-resource NLP, as their linguistic similarity increases confusability for automatic systems. We introduce the first supervised classifier to distinguish standard Catalan from its regional variety Valencian. Our lightweight approach fine-tunes a RoBERTa-base model on a manually curated corpus of 20 000 sentences{---}without any Valencian-specific tools{---}and achieves 98 {\%} accuracy on unseen test data. In a human evaluation of 90 mixed-variety items per reviewer, acceptance rates reached 96.7 {\%} for Valencian and 97.7 {\%} for Catalan (97.2 {\%} overall). We discuss limitations with out-of-distribution inputs and outline future work on confidence calibration and dialect-aware tokenization. Our findings demonstrate that high-impact dialect classification is feasible with minimal resources."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-cerda-etal-2025-building">
<titleInfo>
<title>Building a Lightweight Classifier to Distinguish Closely Related Language Varieties with Limited Supervision: The Case of Catalan vs Valencian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">García Cerdá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">María</namePart>
<namePart type="family">Miró Maestre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miquel</namePart>
<namePart type="family">Canal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ernesto</namePart>
<namePart type="given">Luis</namePart>
<namePart type="family">Estevanell-Valladares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Picazo-Izquierdo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Besik</namePart>
<namePart type="family">Mikaberidze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Ostermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniil</namePart>
<namePart type="family">Gurgurov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Borg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marián</namePart>
<namePart type="family">Šimko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dialectal variation among closely related languages poses a major challenge in low-resource NLP, as their linguistic similarity increases confusability for automatic systems. We introduce the first supervised classifier to distinguish standard Catalan from its regional variety Valencian. Our lightweight approach fine-tunes a RoBERTa-base model on a manually curated corpus of 20 000 sentences—without any Valencian-specific tools—and achieves 98 % accuracy on unseen test data. In a human evaluation of 90 mixed-variety items per reviewer, acceptance rates reached 96.7 % for Valencian and 97.7 % for Catalan (97.2 % overall). We discuss limitations with out-of-distribution inputs and outline future work on confidence calibration and dialect-aware tokenization. Our findings demonstrate that high-impact dialect classification is feasible with minimal resources.</abstract>
<identifier type="citekey">garcia-cerda-etal-2025-building</identifier>
<location>
<url>https://aclanthology.org/2025.lowresnlp-1.2/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>7</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a Lightweight Classifier to Distinguish Closely Related Language Varieties with Limited Supervision: The Case of Catalan vs Valencian
%A García Cerdá, Raúl
%A Miró Maestre, María
%A Canal, Miquel
%Y Estevanell-Valladares, Ernesto Luis
%Y Picazo-Izquierdo, Alicia
%Y Ranasinghe, Tharindu
%Y Mikaberidze, Besik
%Y Ostermann, Simon
%Y Gurgurov, Daniil
%Y Mueller, Philipp
%Y Borg, Claudia
%Y Šimko, Marián
%S Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F garcia-cerda-etal-2025-building
%X Dialectal variation among closely related languages poses a major challenge in low-resource NLP, as their linguistic similarity increases confusability for automatic systems. We introduce the first supervised classifier to distinguish standard Catalan from its regional variety Valencian. Our lightweight approach fine-tunes a RoBERTa-base model on a manually curated corpus of 20 000 sentences—without any Valencian-specific tools—and achieves 98 % accuracy on unseen test data. In a human evaluation of 90 mixed-variety items per reviewer, acceptance rates reached 96.7 % for Valencian and 97.7 % for Catalan (97.2 % overall). We discuss limitations with out-of-distribution inputs and outline future work on confidence calibration and dialect-aware tokenization. Our findings demonstrate that high-impact dialect classification is feasible with minimal resources.
%U https://aclanthology.org/2025.lowresnlp-1.2/
%P 7-11
Markdown (Informal)
[Building a Lightweight Classifier to Distinguish Closely Related Language Varieties with Limited Supervision: The Case of Catalan vs Valencian](https://aclanthology.org/2025.lowresnlp-1.2/) (García Cerdá et al., LowResNLP 2025)
ACL