@inproceedings{zeidler-etal-2025-spanish,
title = "{S}panish Dialect Classification: A Comparative Study of Linguistically Tailored Features, Unigrams and {BERT} Embeddings",
author = "Zeidler, Laura and
Jenkins, Chris and
Mileti{\'c}, Filip and
Schulte Im Walde, Sabine",
editor = "Zhao, Jin and
Wang, Mingyang and
Liu, Zhu",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-srw.36/",
doi = "10.18653/v1/2025.acl-srw.36",
pages = "539--547",
ISBN = "979-8-89176-254-1",
abstract = "The task of automatic dialect classification is typically tackled using traditional machine-learning models with bag-of-words unigram features. We explore two alternative methods for distinguishing dialects across 20 Spanish-speaking countries:(i) Support vector machine and decision tree models were trained on dialectal features tailored to the Spanish dialects, combined with standard unigrams. (ii) A pre-trained BERT model was fine-tuned on the task.Results show that the tailored features generally did not have a positive impact on traditional model performance, but provide a salient way of representing dialects in a content-agnostic manner. The BERT model wins over traditional models but with only a tiny margin, while sacrificing explainability and interpretability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeidler-etal-2025-spanish">
<titleInfo>
<title>Spanish Dialect Classification: A Comparative Study of Linguistically Tailored Features, Unigrams and BERT Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Zeidler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Jenkins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Miletić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabine</namePart>
<namePart type="family">Schulte Im Walde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingyang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-254-1</identifier>
</relatedItem>
<abstract>The task of automatic dialect classification is typically tackled using traditional machine-learning models with bag-of-words unigram features. We explore two alternative methods for distinguishing dialects across 20 Spanish-speaking countries:(i) Support vector machine and decision tree models were trained on dialectal features tailored to the Spanish dialects, combined with standard unigrams. (ii) A pre-trained BERT model was fine-tuned on the task.Results show that the tailored features generally did not have a positive impact on traditional model performance, but provide a salient way of representing dialects in a content-agnostic manner. The BERT model wins over traditional models but with only a tiny margin, while sacrificing explainability and interpretability.</abstract>
<identifier type="citekey">zeidler-etal-2025-spanish</identifier>
<identifier type="doi">10.18653/v1/2025.acl-srw.36</identifier>
<location>
<url>https://aclanthology.org/2025.acl-srw.36/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>539</start>
<end>547</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spanish Dialect Classification: A Comparative Study of Linguistically Tailored Features, Unigrams and BERT Embeddings
%A Zeidler, Laura
%A Jenkins, Chris
%A Miletić, Filip
%A Schulte Im Walde, Sabine
%Y Zhao, Jin
%Y Wang, Mingyang
%Y Liu, Zhu
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-254-1
%F zeidler-etal-2025-spanish
%X The task of automatic dialect classification is typically tackled using traditional machine-learning models with bag-of-words unigram features. We explore two alternative methods for distinguishing dialects across 20 Spanish-speaking countries:(i) Support vector machine and decision tree models were trained on dialectal features tailored to the Spanish dialects, combined with standard unigrams. (ii) A pre-trained BERT model was fine-tuned on the task.Results show that the tailored features generally did not have a positive impact on traditional model performance, but provide a salient way of representing dialects in a content-agnostic manner. The BERT model wins over traditional models but with only a tiny margin, while sacrificing explainability and interpretability.
%R 10.18653/v1/2025.acl-srw.36
%U https://aclanthology.org/2025.acl-srw.36/
%U https://doi.org/10.18653/v1/2025.acl-srw.36
%P 539-547
Markdown (Informal)
[Spanish Dialect Classification: A Comparative Study of Linguistically Tailored Features, Unigrams and BERT Embeddings](https://aclanthology.org/2025.acl-srw.36/) (Zeidler et al., ACL 2025)
ACL