@inproceedings{kumar-etal-2026-singlish,
title = "{S}inglish to {E}nglish Translation with Precision: A Dataset and Language Detection-Driven Masked Modeling for {S}inglish to {E}nglish Translation",
author = "Kumar, Sujit and
Ang, Gerome Kusuma and
Ma, Stephanie Hilary Xinyi and
Ho, Andy Hau Yan and
Khong, Andy",
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-1.280/",
doi = "10.63317/4fw7s9vepnr9",
pages = "3506--3516",
abstract = "Singlish, a creole rooted in English and influenced by Singapore{'}s multilingual and multicultural environment, poses significant challenges for those proficient in standard English due to its unique and often complex lexical and syntactic structures. Despite significant advancements in language translation for both high- and low-resource languages, translating Singlish to English remains largely underexplored. This gap is primarily due to the lack of dedicated datasets for language detection and Singlish-to-English translation, as well as the absence of robust models capable of addressing the unique linguistic challenges posed by Singlish. In this work, we curate a word-level language detection dataset, a Singlish-to-English translation dataset, and propose a Language Detection-driven Masked Language Modelling approach for translating Singlish into English. We evaluate the performance of existing models and the proposed approach on two Singlish-to-English translation datasets, including our proposed SEAT dataset. The results demonstrate that the proposed LD-MLMTrans approach outperforms the baseline model and exhibits high proficiency in Singlish-to-English translation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2026-singlish">
<titleInfo>
<title>Singlish to English Translation with Precision: A Dataset and Language Detection-Driven Masked Modeling for Singlish to English Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sujit</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerome</namePart>
<namePart type="given">Kusuma</namePart>
<namePart type="family">Ang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="given">Hilary</namePart>
<namePart type="given">Xinyi</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="given">Hau</namePart>
<namePart type="given">Yan</namePart>
<namePart type="family">Ho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="family">Khong</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>Singlish, a creole rooted in English and influenced by Singapore’s multilingual and multicultural environment, poses significant challenges for those proficient in standard English due to its unique and often complex lexical and syntactic structures. Despite significant advancements in language translation for both high- and low-resource languages, translating Singlish to English remains largely underexplored. This gap is primarily due to the lack of dedicated datasets for language detection and Singlish-to-English translation, as well as the absence of robust models capable of addressing the unique linguistic challenges posed by Singlish. In this work, we curate a word-level language detection dataset, a Singlish-to-English translation dataset, and propose a Language Detection-driven Masked Language Modelling approach for translating Singlish into English. We evaluate the performance of existing models and the proposed approach on two Singlish-to-English translation datasets, including our proposed SEAT dataset. The results demonstrate that the proposed LD-MLMTrans approach outperforms the baseline model and exhibits high proficiency in Singlish-to-English translation.</abstract>
<identifier type="citekey">kumar-etal-2026-singlish</identifier>
<identifier type="doi">10.63317/4fw7s9vepnr9</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.280/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>3506</start>
<end>3516</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Singlish to English Translation with Precision: A Dataset and Language Detection-Driven Masked Modeling for Singlish to English Translation
%A Kumar, Sujit
%A Ang, Gerome Kusuma
%A Ma, Stephanie Hilary Xinyi
%A Ho, Andy Hau Yan
%A Khong, Andy
%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 kumar-etal-2026-singlish
%X Singlish, a creole rooted in English and influenced by Singapore’s multilingual and multicultural environment, poses significant challenges for those proficient in standard English due to its unique and often complex lexical and syntactic structures. Despite significant advancements in language translation for both high- and low-resource languages, translating Singlish to English remains largely underexplored. This gap is primarily due to the lack of dedicated datasets for language detection and Singlish-to-English translation, as well as the absence of robust models capable of addressing the unique linguistic challenges posed by Singlish. In this work, we curate a word-level language detection dataset, a Singlish-to-English translation dataset, and propose a Language Detection-driven Masked Language Modelling approach for translating Singlish into English. We evaluate the performance of existing models and the proposed approach on two Singlish-to-English translation datasets, including our proposed SEAT dataset. The results demonstrate that the proposed LD-MLMTrans approach outperforms the baseline model and exhibits high proficiency in Singlish-to-English translation.
%R 10.63317/4fw7s9vepnr9
%U https://aclanthology.org/2026.lrec-1.280/
%U https://doi.org/10.63317/4fw7s9vepnr9
%P 3506-3516
Markdown (Informal)
[Singlish to English Translation with Precision: A Dataset and Language Detection-Driven Masked Modeling for Singlish to English Translation](https://aclanthology.org/2026.lrec-1.280/) (Kumar et al., LREC 2026)
ACL