@inproceedings{chelombitko-etal-2026-subword,
title = "Subword-Based Comparative Linguistics across 242 Languages Using {W}ikipedia Glottosets",
author = {Chelombitko, Iaroslav and
H{\"a}m{\"a}l{\"a}inen, Mika and
Komissarov, Aleksey},
editor = "Adelani, David Ifeoluwa and
Alabi, Jesujoba and
Arnett, Catherine and
Chang, Tyler and
Downey, C.M. and
Goldman, Omer and
Li, Senyu and
Miranda, Lester James Validad and
Qi, Jirui and
Stap, David and
Winata, Genta Indra and
Zhang, Xinyu Crystina",
booktitle = "Proceedings of the 6th Workshop on Multilingual Representation Learning ({MRL} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mrl-1.4/",
pages = "37--52",
ISBN = "979-8-89176-469-9",
abstract = "We release **morphoBPE**, a framework for training and comparing per-language BPE tokenizers across 242 Latin- and Cyrillic-script languages built from Wikipedia *glottosets* (per-language TF-DF lexicons), with four diagnostic evaluations of what BPE captures across scripts. Unsupervised language identification by token count reaches 13.8{\%} accuracy across 320 Latin-script languages, against 19.83{\%} for supervised fastText `lid.176{`}, which returns zero for 147 of them because they fall outside its 176-language alphabet, including our best performers (Lak 81.5{\%}, Cree 80.6{\%}, Inuktitut 63.8{\%}, Kabardian 60.1{\%}). BPE aligns with morpheme boundaries at $F_1 = 0.28$ across 15 languages (Morfessor: 0.43), and beats supervised character-*n*-gram cross-lingual transfer by +37{\%} $F_1$ across six pairs where labeled morphology is unavailable. BPE distance correlates moderately with Glottolog phylogeny (Mantel $r = 0.329$). We position per-language BPE as a coverage-first diagnostic for languages outside the supervised long tail, not as a substitute for supervised methods where labels exist."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chelombitko-etal-2026-subword">
<titleInfo>
<title>Subword-Based Comparative Linguistics across 242 Languages Using Wikipedia Glottosets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iaroslav</namePart>
<namePart type="family">Chelombitko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksey</namePart>
<namePart type="family">Komissarov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Downey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Goldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lester</namePart>
<namePart type="given">James</namePart>
<namePart type="given">Validad</namePart>
<namePart type="family">Miranda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jirui</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="given">Crystina</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-469-9</identifier>
</relatedItem>
<abstract>We release **morphoBPE**, a framework for training and comparing per-language BPE tokenizers across 242 Latin- and Cyrillic-script languages built from Wikipedia *glottosets* (per-language TF-DF lexicons), with four diagnostic evaluations of what BPE captures across scripts. Unsupervised language identification by token count reaches 13.8% accuracy across 320 Latin-script languages, against 19.83% for supervised fastText ‘lid.176‘, which returns zero for 147 of them because they fall outside its 176-language alphabet, including our best performers (Lak 81.5%, Cree 80.6%, Inuktitut 63.8%, Kabardian 60.1%). BPE aligns with morpheme boundaries at F₁ = 0.28 across 15 languages (Morfessor: 0.43), and beats supervised character-*n*-gram cross-lingual transfer by +37% F₁ across six pairs where labeled morphology is unavailable. BPE distance correlates moderately with Glottolog phylogeny (Mantel r = 0.329). We position per-language BPE as a coverage-first diagnostic for languages outside the supervised long tail, not as a substitute for supervised methods where labels exist.</abstract>
<identifier type="citekey">chelombitko-etal-2026-subword</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.4/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>37</start>
<end>52</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Subword-Based Comparative Linguistics across 242 Languages Using Wikipedia Glottosets
%A Chelombitko, Iaroslav
%A Hämäläinen, Mika
%A Komissarov, Aleksey
%Y Adelani, David Ifeoluwa
%Y Alabi, Jesujoba
%Y Arnett, Catherine
%Y Chang, Tyler
%Y Downey, C. M.
%Y Goldman, Omer
%Y Li, Senyu
%Y Miranda, Lester James Validad
%Y Qi, Jirui
%Y Stap, David
%Y Winata, Genta Indra
%Y Zhang, Xinyu Crystina
%S Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-469-9
%F chelombitko-etal-2026-subword
%X We release **morphoBPE**, a framework for training and comparing per-language BPE tokenizers across 242 Latin- and Cyrillic-script languages built from Wikipedia *glottosets* (per-language TF-DF lexicons), with four diagnostic evaluations of what BPE captures across scripts. Unsupervised language identification by token count reaches 13.8% accuracy across 320 Latin-script languages, against 19.83% for supervised fastText ‘lid.176‘, which returns zero for 147 of them because they fall outside its 176-language alphabet, including our best performers (Lak 81.5%, Cree 80.6%, Inuktitut 63.8%, Kabardian 60.1%). BPE aligns with morpheme boundaries at F₁ = 0.28 across 15 languages (Morfessor: 0.43), and beats supervised character-*n*-gram cross-lingual transfer by +37% F₁ across six pairs where labeled morphology is unavailable. BPE distance correlates moderately with Glottolog phylogeny (Mantel r = 0.329). We position per-language BPE as a coverage-first diagnostic for languages outside the supervised long tail, not as a substitute for supervised methods where labels exist.
%U https://aclanthology.org/2026.mrl-1.4/
%P 37-52
Markdown (Informal)
[Subword-Based Comparative Linguistics across 242 Languages Using Wikipedia Glottosets](https://aclanthology.org/2026.mrl-1.4/) (Chelombitko et al., MRL 2026)
ACL