@inproceedings{salice-etal-2026-insights,
title = "Insights from {R}omanized {M}anipuri Social Media Text: A Transliteration Corpus and Variation Analysis",
author = "Salice, Maisang Kamei and
Ranbir Singh, Sanasam and
Sarmah, Priyankoo",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.147/",
doi = "10.63317/3uqwwrf7jvvo",
pages = "1878--1888",
abstract = "This paper presents the first large-scale study of Romanized Manipuri, a low-resource Indic language widely used by native speakers on social media. Social media text is highly informal and often noisy, posing challenges for natural language processing tasks; therefore, normalization through back-transliteration is essential. We construct a Romanized Manipuri to Manipuri{--}Bengali script back-transliteration corpus from YouTube comments, capturing diverse informal writing styles and orthographic variations. The dataset is analyzed to examine variation patterns at two levels: character-level inconsistencies and pragmatic stylistic variations influenced by user writing behavior. We also compare social media romanization with formal transliteration conventions, including standardized romanization schemes and textbook-based systems. Furthermore, we evaluate Transformer model at both character and subword levels and conduct a detailed error analyses to identify key challenges affecting back-transliteration performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salice-etal-2026-insights">
<titleInfo>
<title>Insights from Romanized Manipuri Social Media Text: A Transliteration Corpus and Variation Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maisang</namePart>
<namePart type="given">Kamei</namePart>
<namePart type="family">Salice</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanasam</namePart>
<namePart type="family">Ranbir Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyankoo</namePart>
<namePart type="family">Sarmah</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the first large-scale study of Romanized Manipuri, a low-resource Indic language widely used by native speakers on social media. Social media text is highly informal and often noisy, posing challenges for natural language processing tasks; therefore, normalization through back-transliteration is essential. We construct a Romanized Manipuri to Manipuri–Bengali script back-transliteration corpus from YouTube comments, capturing diverse informal writing styles and orthographic variations. The dataset is analyzed to examine variation patterns at two levels: character-level inconsistencies and pragmatic stylistic variations influenced by user writing behavior. We also compare social media romanization with formal transliteration conventions, including standardized romanization schemes and textbook-based systems. Furthermore, we evaluate Transformer model at both character and subword levels and conduct a detailed error analyses to identify key challenges affecting back-transliteration performance.</abstract>
<identifier type="citekey">salice-etal-2026-insights</identifier>
<identifier type="doi">10.63317/3uqwwrf7jvvo</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.147/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1878</start>
<end>1888</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Insights from Romanized Manipuri Social Media Text: A Transliteration Corpus and Variation Analysis
%A Salice, Maisang Kamei
%A Ranbir Singh, Sanasam
%A Sarmah, Priyankoo
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F salice-etal-2026-insights
%X This paper presents the first large-scale study of Romanized Manipuri, a low-resource Indic language widely used by native speakers on social media. Social media text is highly informal and often noisy, posing challenges for natural language processing tasks; therefore, normalization through back-transliteration is essential. We construct a Romanized Manipuri to Manipuri–Bengali script back-transliteration corpus from YouTube comments, capturing diverse informal writing styles and orthographic variations. The dataset is analyzed to examine variation patterns at two levels: character-level inconsistencies and pragmatic stylistic variations influenced by user writing behavior. We also compare social media romanization with formal transliteration conventions, including standardized romanization schemes and textbook-based systems. Furthermore, we evaluate Transformer model at both character and subword levels and conduct a detailed error analyses to identify key challenges affecting back-transliteration performance.
%R 10.63317/3uqwwrf7jvvo
%U https://aclanthology.org/2026.lrec-1.147/
%U https://doi.org/10.63317/3uqwwrf7jvvo
%P 1878-1888
Markdown (Informal)
[Insights from Romanized Manipuri Social Media Text: A Transliteration Corpus and Variation Analysis](https://aclanthology.org/2026.lrec-1.147/) (Salice et al., LREC 2026)
ACL