@inproceedings{singh-2026-one,
title = "One Meaning, Many Romanizations: Selective Stability of Multilingual Representations under Informal {I}ndic {R}omanization",
author = "Singh, Divyajot",
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-1.29/",
pages = "366--376",
ISBN = "979-8-89176-469-9",
abstract = "Romanized writing is a common interface for speakers of Indic languages, but it is intrinsically many-to-one: several informal spellings express the same underlying utterance. Existing evaluations typically use one canonical transliteration and may therefore overestimate robustness. We introduce a 4,000-set convention-profile benchmark alongside native-script, human-Romanized, and human-attested equivalence views in Bengali, Hindi, Tamil, and Telugu. Across twelve pretrained and instruction-tuned models from three families, we measure token fragmentation, layer-wise representation dispersion, language-modeling loss, and cross-script retrieval instability. We formalize the target property asemph{selective stability}{---}equivalent spellings must contract while distinct meanings stay separated{---}operationalize it with a normalized within-equivalence distance, and test whether it predicts retrieval failure beyond token fertility. We find that cross-script invariance is aemph{transient} phase in depth whose location is architecture-dependent, that representation distance predicts inconsistency better than fertility (ROC-AUC .774 vs. .634 on the small instruction model), and that a lightweight low-rank repair trained only on canonical and synthetic variants transfers to unseen natural spellings, held-out convention families, and unseen languages without improving Romanized reading comprehension. A per-language decomposition shows that the phase is also largely language-conditional: one Gemma{~}9B layer retrieves 90.4"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-2026-one">
<titleInfo>
<title>One Meaning, Many Romanizations: Selective Stability of Multilingual Representations under Informal Indic Romanization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Divyajot</namePart>
<namePart type="family">Singh</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>Romanized writing is a common interface for speakers of Indic languages, but it is intrinsically many-to-one: several informal spellings express the same underlying utterance. Existing evaluations typically use one canonical transliteration and may therefore overestimate robustness. We introduce a 4,000-set convention-profile benchmark alongside native-script, human-Romanized, and human-attested equivalence views in Bengali, Hindi, Tamil, and Telugu. Across twelve pretrained and instruction-tuned models from three families, we measure token fragmentation, layer-wise representation dispersion, language-modeling loss, and cross-script retrieval instability. We formalize the target property asemphselective stability—equivalent spellings must contract while distinct meanings stay separated—operationalize it with a normalized within-equivalence distance, and test whether it predicts retrieval failure beyond token fertility. We find that cross-script invariance is aemphtransient phase in depth whose location is architecture-dependent, that representation distance predicts inconsistency better than fertility (ROC-AUC .774 vs. .634 on the small instruction model), and that a lightweight low-rank repair trained only on canonical and synthetic variants transfers to unseen natural spellings, held-out convention families, and unseen languages without improving Romanized reading comprehension. A per-language decomposition shows that the phase is also largely language-conditional: one Gemma 9B layer retrieves 90.4</abstract>
<identifier type="citekey">singh-2026-one</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.29/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>366</start>
<end>376</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T One Meaning, Many Romanizations: Selective Stability of Multilingual Representations under Informal Indic Romanization
%A Singh, Divyajot
%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 singh-2026-one
%X Romanized writing is a common interface for speakers of Indic languages, but it is intrinsically many-to-one: several informal spellings express the same underlying utterance. Existing evaluations typically use one canonical transliteration and may therefore overestimate robustness. We introduce a 4,000-set convention-profile benchmark alongside native-script, human-Romanized, and human-attested equivalence views in Bengali, Hindi, Tamil, and Telugu. Across twelve pretrained and instruction-tuned models from three families, we measure token fragmentation, layer-wise representation dispersion, language-modeling loss, and cross-script retrieval instability. We formalize the target property asemphselective stability—equivalent spellings must contract while distinct meanings stay separated—operationalize it with a normalized within-equivalence distance, and test whether it predicts retrieval failure beyond token fertility. We find that cross-script invariance is aemphtransient phase in depth whose location is architecture-dependent, that representation distance predicts inconsistency better than fertility (ROC-AUC .774 vs. .634 on the small instruction model), and that a lightweight low-rank repair trained only on canonical and synthetic variants transfers to unseen natural spellings, held-out convention families, and unseen languages without improving Romanized reading comprehension. A per-language decomposition shows that the phase is also largely language-conditional: one Gemma 9B layer retrieves 90.4
%U https://aclanthology.org/2026.mrl-1.29/
%P 366-376
Markdown (Informal)
[One Meaning, Many Romanizations: Selective Stability of Multilingual Representations under Informal Indic Romanization](https://aclanthology.org/2026.mrl-1.29/) (Singh, MRL 2026)
ACL