@inproceedings{gutkin-etal-2026-confusable,
title = "Confusable Characters as Endangered Language Markers: The Case of {N}orth {C}aucasus Writing Systems",
author = "Gutkin, Alexander and
Benton, Adrian and
Kirov, Christo and
Roark, Brian",
editor = "Gorman, Kyle",
booktitle = "Proceedings of the Third Workshop on Computation and Written Language ({CAWL} 2026) @ {LREC} 2026",
month = jun,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.cawl-1.5/",
doi = "10.63317/4ucp22rs54d9",
pages = "50--63",
abstract = "The Abkhaz-Adyghe and Nakh-Daghestanian language families encompass 35 living languages that possess arguably the most complex modern Cyrillic orthographies due to their very sophisticated phonology. The relevant online data displays idiosyncratic patterns among which the use of confusable characters in input methods is the most prevalent. This work studies one such character{---}letter palochka{---}that is shared by most of the writing systems in question. We investigate whether patterns including variants of this character can act as markers of these languages in large-scale web-crawled data. We use GlotLID, a wide-coverage off-the-shelf language identification (LID) model, to label paragraph-level web text that contains a palochka confusable, and estimate the effect of confusable character normalization on the quality of GlotLID{'}s predictions in 14 supported North Caucasian languages. According to GlotLID, the normalization significantly increases the recall (discovery of new language data) for some languages, while degrading it for others. However, manual evaluation reveals that overall, only 41{\%} of ensuing wins and 46{\%} of losses are accurate due to GlotLID prediction errors. We argue that, despite finding useful signals, higher precision LID approaches tailored to these long-tail languages are needed to improve the quality of mined data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gutkin-etal-2026-confusable">
<titleInfo>
<title>Confusable Characters as Endangered Language Markers: The Case of North Caucasus Writing Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Gutkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="family">Benton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christo</namePart>
<namePart type="family">Kirov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Roark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Computation and Written Language (CAWL 2026) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Gorman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Abkhaz-Adyghe and Nakh-Daghestanian language families encompass 35 living languages that possess arguably the most complex modern Cyrillic orthographies due to their very sophisticated phonology. The relevant online data displays idiosyncratic patterns among which the use of confusable characters in input methods is the most prevalent. This work studies one such character—letter palochka—that is shared by most of the writing systems in question. We investigate whether patterns including variants of this character can act as markers of these languages in large-scale web-crawled data. We use GlotLID, a wide-coverage off-the-shelf language identification (LID) model, to label paragraph-level web text that contains a palochka confusable, and estimate the effect of confusable character normalization on the quality of GlotLID’s predictions in 14 supported North Caucasian languages. According to GlotLID, the normalization significantly increases the recall (discovery of new language data) for some languages, while degrading it for others. However, manual evaluation reveals that overall, only 41% of ensuing wins and 46% of losses are accurate due to GlotLID prediction errors. We argue that, despite finding useful signals, higher precision LID approaches tailored to these long-tail languages are needed to improve the quality of mined data.</abstract>
<identifier type="citekey">gutkin-etal-2026-confusable</identifier>
<identifier type="doi">10.63317/4ucp22rs54d9</identifier>
<location>
<url>https://aclanthology.org/2026.cawl-1.5/</url>
</location>
<part>
<date>2026-06</date>
<extent unit="page">
<start>50</start>
<end>63</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Confusable Characters as Endangered Language Markers: The Case of North Caucasus Writing Systems
%A Gutkin, Alexander
%A Benton, Adrian
%A Kirov, Christo
%A Roark, Brian
%Y Gorman, Kyle
%S Proceedings of the Third Workshop on Computation and Written Language (CAWL 2026) @ LREC 2026
%D 2026
%8 June
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F gutkin-etal-2026-confusable
%X The Abkhaz-Adyghe and Nakh-Daghestanian language families encompass 35 living languages that possess arguably the most complex modern Cyrillic orthographies due to their very sophisticated phonology. The relevant online data displays idiosyncratic patterns among which the use of confusable characters in input methods is the most prevalent. This work studies one such character—letter palochka—that is shared by most of the writing systems in question. We investigate whether patterns including variants of this character can act as markers of these languages in large-scale web-crawled data. We use GlotLID, a wide-coverage off-the-shelf language identification (LID) model, to label paragraph-level web text that contains a palochka confusable, and estimate the effect of confusable character normalization on the quality of GlotLID’s predictions in 14 supported North Caucasian languages. According to GlotLID, the normalization significantly increases the recall (discovery of new language data) for some languages, while degrading it for others. However, manual evaluation reveals that overall, only 41% of ensuing wins and 46% of losses are accurate due to GlotLID prediction errors. We argue that, despite finding useful signals, higher precision LID approaches tailored to these long-tail languages are needed to improve the quality of mined data.
%R 10.63317/4ucp22rs54d9
%U https://aclanthology.org/2026.cawl-1.5/
%U https://doi.org/10.63317/4ucp22rs54d9
%P 50-63
Markdown (Informal)
[Confusable Characters as Endangered Language Markers: The Case of North Caucasus Writing Systems](https://aclanthology.org/2026.cawl-1.5/) (Gutkin et al., CAWL 2026)
ACL