@inproceedings{signoroni-etal-2026-rebelot,
title = "Rebel{\`o}t: Datasets and Token-Level Language Identification for {L}ombard-{I}talian-{E}nglish Code-Mixing",
author = "Signoroni, Edoardo and
Bedna{\v{r}}{\'i}kov{\'a}, Emma and
Rychly, Pavel",
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-1.25/",
doi = "10.63317/4yids37agyxu",
pages = "253--262",
abstract = "Lombard is an endangered and under-resourced Gallo-Italic language variety that exists with Standard Italian. As with other language varieties of Italy, code-switching and code-mixing is common between Lombard and Italian in everyday conversation and with English, online. This linguistic complexity, and the lack of a unified written standard, poses challenges for Natural Language Processing tools. We introduce Rebel{\`o}t, a novel multi-domain, token-level annotated dataset for Lombard-Italian-English code-mixing. Furthermore, we develop and evaluate three variants of a token-level Language Identification (LID) tool based on a pre-trained encoder architecture, fine-tuned using both authentic data from our corpus and synthetically generated code-mixed text. Our evaluation demonstrates that the optimal model variant achieves an accuracy of over 0.99 on token-level prediction, and substantially outperforms widely used off-the-shelf LID baselines at sentence-level."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="signoroni-etal-2026-rebelot">
<titleInfo>
<title>Rebelòt: Datasets and Token-Level Language Identification for Lombard-Italian-English Code-Mixing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="family">Signoroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emma</namePart>
<namePart type="family">Bednaříková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Rychly</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>Lombard is an endangered and under-resourced Gallo-Italic language variety that exists with Standard Italian. As with other language varieties of Italy, code-switching and code-mixing is common between Lombard and Italian in everyday conversation and with English, online. This linguistic complexity, and the lack of a unified written standard, poses challenges for Natural Language Processing tools. We introduce Rebelòt, a novel multi-domain, token-level annotated dataset for Lombard-Italian-English code-mixing. Furthermore, we develop and evaluate three variants of a token-level Language Identification (LID) tool based on a pre-trained encoder architecture, fine-tuned using both authentic data from our corpus and synthetically generated code-mixed text. Our evaluation demonstrates that the optimal model variant achieves an accuracy of over 0.99 on token-level prediction, and substantially outperforms widely used off-the-shelf LID baselines at sentence-level.</abstract>
<identifier type="citekey">signoroni-etal-2026-rebelot</identifier>
<identifier type="doi">10.63317/4yids37agyxu</identifier>
<location>
<url>https://aclanthology.org/2026.sigul-1.25/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>253</start>
<end>262</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rebelòt: Datasets and Token-Level Language Identification for Lombard-Italian-English Code-Mixing
%A Signoroni, Edoardo
%A Bednaříková, Emma
%A Rychly, Pavel
%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 signoroni-etal-2026-rebelot
%X Lombard is an endangered and under-resourced Gallo-Italic language variety that exists with Standard Italian. As with other language varieties of Italy, code-switching and code-mixing is common between Lombard and Italian in everyday conversation and with English, online. This linguistic complexity, and the lack of a unified written standard, poses challenges for Natural Language Processing tools. We introduce Rebelòt, a novel multi-domain, token-level annotated dataset for Lombard-Italian-English code-mixing. Furthermore, we develop and evaluate three variants of a token-level Language Identification (LID) tool based on a pre-trained encoder architecture, fine-tuned using both authentic data from our corpus and synthetically generated code-mixed text. Our evaluation demonstrates that the optimal model variant achieves an accuracy of over 0.99 on token-level prediction, and substantially outperforms widely used off-the-shelf LID baselines at sentence-level.
%R 10.63317/4yids37agyxu
%U https://aclanthology.org/2026.sigul-1.25/
%U https://doi.org/10.63317/4yids37agyxu
%P 253-262
Markdown (Informal)
[Rebelòt: Datasets and Token-Level Language Identification for Lombard-Italian-English Code-Mixing](https://aclanthology.org/2026.sigul-1.25/) (Signoroni et al., SIGUL-EURALI-DCLRL 2026)
ACL