@inproceedings{fedorova-etal-2026-openlid,
title = "{O}pen{LID}-v3: Improving the Precision of Closely Related Language Identification {--} An Experience Report",
author = "Fedorova, Mariia and
Arefyev, Nikolay and
Buljan, Maja and
Helcl, Jind{\v{r}}ich and
Oepen, Stephan and
R{\o}nningstad, Egil and
Scherrer, Yves",
booktitle = "Proceedings of the 13th Workshop on {NLP} for Similar Languages, Varieties and Dialects",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.vardial-1.23/",
pages = "275--292",
abstract = "Language identification (LID) is an essential step in building high-quality multilingual datasets from web data. Existing LID tools (such as OpenLID or GlotLID) often struggle to identify closely related languages and to distinguish valid natural language from noise, which contaminates language-specific subsets, especially for low-resource languages. In this work we extend the OpenLID classifier by adding more training data, merging problematic language variant clusters, and introducing a special label for marking noise. We call this extended system OpenLID-v3 and evaluate it against GlotLID on multiple benchmarks. During the development we focus on three groups of closely related languages (Bosnian, Croatian, and Serbian; Romance varieties of Northern Italy and Southern France; and Scandinavian languages) and contribute new evaluation datasets where existing ones are inadequate. We find that ensemble approaches improve precision but also substantially reduce coverage for low-resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fedorova-etal-2026-openlid">
<titleInfo>
<title>OpenLID-v3: Improving the Precision of Closely Related Language Identification – An Experience Report</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mariia</namePart>
<namePart type="family">Fedorova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolay</namePart>
<namePart type="family">Arefyev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Buljan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jindřich</namePart>
<namePart type="family">Helcl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephan</namePart>
<namePart type="family">Oepen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Egil</namePart>
<namePart type="family">Rønningstad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language identification (LID) is an essential step in building high-quality multilingual datasets from web data. Existing LID tools (such as OpenLID or GlotLID) often struggle to identify closely related languages and to distinguish valid natural language from noise, which contaminates language-specific subsets, especially for low-resource languages. In this work we extend the OpenLID classifier by adding more training data, merging problematic language variant clusters, and introducing a special label for marking noise. We call this extended system OpenLID-v3 and evaluate it against GlotLID on multiple benchmarks. During the development we focus on three groups of closely related languages (Bosnian, Croatian, and Serbian; Romance varieties of Northern Italy and Southern France; and Scandinavian languages) and contribute new evaluation datasets where existing ones are inadequate. We find that ensemble approaches improve precision but also substantially reduce coverage for low-resource languages.</abstract>
<identifier type="citekey">fedorova-etal-2026-openlid</identifier>
<location>
<url>https://aclanthology.org/2026.vardial-1.23/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>275</start>
<end>292</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OpenLID-v3: Improving the Precision of Closely Related Language Identification – An Experience Report
%A Fedorova, Mariia
%A Arefyev, Nikolay
%A Buljan, Maja
%A Helcl, Jindřich
%A Oepen, Stephan
%A Rønningstad, Egil
%A Scherrer, Yves
%S Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%F fedorova-etal-2026-openlid
%X Language identification (LID) is an essential step in building high-quality multilingual datasets from web data. Existing LID tools (such as OpenLID or GlotLID) often struggle to identify closely related languages and to distinguish valid natural language from noise, which contaminates language-specific subsets, especially for low-resource languages. In this work we extend the OpenLID classifier by adding more training data, merging problematic language variant clusters, and introducing a special label for marking noise. We call this extended system OpenLID-v3 and evaluate it against GlotLID on multiple benchmarks. During the development we focus on three groups of closely related languages (Bosnian, Croatian, and Serbian; Romance varieties of Northern Italy and Southern France; and Scandinavian languages) and contribute new evaluation datasets where existing ones are inadequate. We find that ensemble approaches improve precision but also substantially reduce coverage for low-resource languages.
%U https://aclanthology.org/2026.vardial-1.23/
%P 275-292
Markdown (Informal)
[OpenLID-v3: Improving the Precision of Closely Related Language Identification – An Experience Report](https://aclanthology.org/2026.vardial-1.23/) (Fedorova et al., VarDial 2026)
ACL
- Mariia Fedorova, Nikolay Arefyev, Maja Buljan, Jindřich Helcl, Stephan Oepen, Egil Rønningstad, and Yves Scherrer. 2026. OpenLID-v3: Improving the Precision of Closely Related Language Identification – An Experience Report. In Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects, pages 275–292, Rabat, Morocco. Association for Computational Linguistics.