@inproceedings{aranberri-2026-register,
title = "Register Sensitivity in Scalar {MT} Evaluation: Evidence from {S}panish{--}{B}asque Informal Discourse",
author = "Aranberri, Nora",
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-1.2/",
doi = "10.63317/4ig5743iz2r3",
pages = "19--32",
abstract = "Automatic scalar metrics are widely used for machine translation (MT) evaluation, yet their behavior under sociolinguistic variation remains underexplored, particularly in under-resourced and minority-language contexts. We present a small, controlled empirical analysis of reference-based evaluation in Spanish{--}Basque informal discourse. Register is operationalized as indexical density, capturing dialectal forms, informal lexicon, code-switching and orthographic stylization. Across two MT systems and prompting conditions, sentence-level scores from chrF++, COMET-DA, and XCOMET-XL show a consistent negative association with indexical density under the original informal reference. In a reference-perturbation design that holds MT outputs constant while replacing the informal reference with a standardized Batua version, scores increase systematically, particularly for high-density items, and the density{--}score association weakens. These results provide controlled evidence that evaluation outcomes in this setting depend in part on reference register configuration. In minority-language and informal domains, reference design choices may influence how translation quality is measured and interpreted."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aranberri-2026-register">
<titleInfo>
<title>Register Sensitivity in Scalar MT Evaluation: Evidence from Spanish–Basque Informal Discourse</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Aranberri</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>Automatic scalar metrics are widely used for machine translation (MT) evaluation, yet their behavior under sociolinguistic variation remains underexplored, particularly in under-resourced and minority-language contexts. We present a small, controlled empirical analysis of reference-based evaluation in Spanish–Basque informal discourse. Register is operationalized as indexical density, capturing dialectal forms, informal lexicon, code-switching and orthographic stylization. Across two MT systems and prompting conditions, sentence-level scores from chrF++, COMET-DA, and XCOMET-XL show a consistent negative association with indexical density under the original informal reference. In a reference-perturbation design that holds MT outputs constant while replacing the informal reference with a standardized Batua version, scores increase systematically, particularly for high-density items, and the density–score association weakens. These results provide controlled evidence that evaluation outcomes in this setting depend in part on reference register configuration. In minority-language and informal domains, reference design choices may influence how translation quality is measured and interpreted.</abstract>
<identifier type="citekey">aranberri-2026-register</identifier>
<identifier type="doi">10.63317/4ig5743iz2r3</identifier>
<location>
<url>https://aclanthology.org/2026.sigul-1.2/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>19</start>
<end>32</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Register Sensitivity in Scalar MT Evaluation: Evidence from Spanish–Basque Informal Discourse
%A Aranberri, Nora
%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 aranberri-2026-register
%X Automatic scalar metrics are widely used for machine translation (MT) evaluation, yet their behavior under sociolinguistic variation remains underexplored, particularly in under-resourced and minority-language contexts. We present a small, controlled empirical analysis of reference-based evaluation in Spanish–Basque informal discourse. Register is operationalized as indexical density, capturing dialectal forms, informal lexicon, code-switching and orthographic stylization. Across two MT systems and prompting conditions, sentence-level scores from chrF++, COMET-DA, and XCOMET-XL show a consistent negative association with indexical density under the original informal reference. In a reference-perturbation design that holds MT outputs constant while replacing the informal reference with a standardized Batua version, scores increase systematically, particularly for high-density items, and the density–score association weakens. These results provide controlled evidence that evaluation outcomes in this setting depend in part on reference register configuration. In minority-language and informal domains, reference design choices may influence how translation quality is measured and interpreted.
%R 10.63317/4ig5743iz2r3
%U https://aclanthology.org/2026.sigul-1.2/
%U https://doi.org/10.63317/4ig5743iz2r3
%P 19-32
Markdown (Informal)
[Register Sensitivity in Scalar MT Evaluation: Evidence from Spanish–Basque Informal Discourse](https://aclanthology.org/2026.sigul-1.2/) (Aranberri, SIGUL-EURALI-DCLRL 2026)
ACL