@inproceedings{dias-etal-2026-sinmix2mono,
title = "{S}in{M}ix2{M}ono: A Dataset for Code-mixed {R}omanized {S}inhala Translation and Transliteration",
author = "Dias, Rukshan and
Sumanathilaka, Deshan and
Sindhujan, Archchana and
Nimna, Minidu",
editor = "Shterionov, Dimitar and
Vanmassenhove, Eva and
De Sisto, Mirella and
Blain, Fred and
Pourmostafa Roshan Sharami, Javad and
Lepp, Lisa and
Manna, Chiara and
Rescigno, Argentina Anna and
Karakanta, Alina and
Rigouts Terryn, Ayla and
Lardelli, Manuel and
Resende, Natalia and
Murgolo, Elena and
Hackenbuchner, Jani{\c{c}}a and
Zaretskaya, Anna and
Espl{\`a}-Gomis, Miquel and
Etchegoyhen, Thierry and
Gromann, Dagmar and
Bawden, Rachel and
Haddow, Barry and
Szoc, Sara and
Forcada, Mikel and
Moniz, Helena",
booktitle = "Proceedings of the 26th Annual Conference of the {E}uropean Association for Machine Translation (Volume 1)",
month = jun,
year = "2026",
address = "Tilburg, The Netherlands",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2026.eamt-1.10/",
pages = "114--129",
ISBN = "9789403901411",
abstract = "Code-mixed and Romanized texts are widely used in digital content, yet they remain largely underexplored for many low-resource languages, including Sinhala. The scarcity of high-quality parallel data has limited progress on downstream tasks, such as machine translation and transliteration. We introduce SinMix2Mono, the largest manually annotated parallel training dataset, followed by the first gold standard benchmark and code-mixed transliteration ambiguity corpora for code-mixed romanized Sinhala to Sinhala conversion. The dataset comprises approximately 25,000 real-world sentences collected from social media, covering diverse domains and authentic code-mixing patterns. To ensure high-quality translations, we used an annotation pipeline that combined rule-based transliteration, LLM-assisted translation, and human validation. The golden test dataset, which includes 2549 sentences, and the code-mixed transliteration ambiguity test were validated by three annotators, yielding Gwet{'}s AC1 scores of 0.7465 and 0.7068, respectively. We benchmarked nine systems, including statistical, neural and commercial LLMs. SinMix2Mono provides a robust training and evaluation resource, establishing a strong benchmark for future research on Sinhala code-mixed translation and transliteration."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dias-etal-2026-sinmix2mono">
<titleInfo>
<title>SinMix2Mono: A Dataset for Code-mixed Romanized Sinhala Translation and Transliteration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rukshan</namePart>
<namePart type="family">Dias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deshan</namePart>
<namePart type="family">Sumanathilaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Archchana</namePart>
<namePart type="family">Sindhujan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minidu</namePart>
<namePart type="family">Nimna</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 26th Annual Conference of the European Association for Machine Translation (Volume 1)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitar</namePart>
<namePart type="family">Shterionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Vanmassenhove</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">De Sisto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fred</namePart>
<namePart type="family">Blain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javad</namePart>
<namePart type="family">Pourmostafa Roshan Sharami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Lepp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chiara</namePart>
<namePart type="family">Manna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Argentina</namePart>
<namePart type="given">Anna</namePart>
<namePart type="family">Rescigno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Karakanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayla</namePart>
<namePart type="family">Rigouts Terryn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Lardelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Resende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Murgolo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janiça</namePart>
<namePart type="family">Hackenbuchner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Zaretskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miquel</namePart>
<namePart type="family">Esplà-Gomis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Etchegoyhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dagmar</namePart>
<namePart type="family">Gromann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Szoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Tilburg, The Netherlands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">9789403901411</identifier>
</relatedItem>
<abstract>Code-mixed and Romanized texts are widely used in digital content, yet they remain largely underexplored for many low-resource languages, including Sinhala. The scarcity of high-quality parallel data has limited progress on downstream tasks, such as machine translation and transliteration. We introduce SinMix2Mono, the largest manually annotated parallel training dataset, followed by the first gold standard benchmark and code-mixed transliteration ambiguity corpora for code-mixed romanized Sinhala to Sinhala conversion. The dataset comprises approximately 25,000 real-world sentences collected from social media, covering diverse domains and authentic code-mixing patterns. To ensure high-quality translations, we used an annotation pipeline that combined rule-based transliteration, LLM-assisted translation, and human validation. The golden test dataset, which includes 2549 sentences, and the code-mixed transliteration ambiguity test were validated by three annotators, yielding Gwet’s AC1 scores of 0.7465 and 0.7068, respectively. We benchmarked nine systems, including statistical, neural and commercial LLMs. SinMix2Mono provides a robust training and evaluation resource, establishing a strong benchmark for future research on Sinhala code-mixed translation and transliteration.</abstract>
<identifier type="citekey">dias-etal-2026-sinmix2mono</identifier>
<location>
<url>https://aclanthology.org/2026.eamt-1.10/</url>
</location>
<part>
<date>2026-06</date>
<extent unit="page">
<start>114</start>
<end>129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SinMix2Mono: A Dataset for Code-mixed Romanized Sinhala Translation and Transliteration
%A Dias, Rukshan
%A Sumanathilaka, Deshan
%A Sindhujan, Archchana
%A Nimna, Minidu
%Y Shterionov, Dimitar
%Y Vanmassenhove, Eva
%Y De Sisto, Mirella
%Y Blain, Fred
%Y Pourmostafa Roshan Sharami, Javad
%Y Lepp, Lisa
%Y Manna, Chiara
%Y Rescigno, Argentina Anna
%Y Karakanta, Alina
%Y Rigouts Terryn, Ayla
%Y Lardelli, Manuel
%Y Resende, Natalia
%Y Murgolo, Elena
%Y Hackenbuchner, Janiça
%Y Zaretskaya, Anna
%Y Esplà-Gomis, Miquel
%Y Etchegoyhen, Thierry
%Y Gromann, Dagmar
%Y Bawden, Rachel
%Y Haddow, Barry
%Y Szoc, Sara
%Y Forcada, Mikel
%Y Moniz, Helena
%S Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)
%D 2026
%8 June
%I European Association for Machine Translation
%C Tilburg, The Netherlands
%@ 9789403901411
%F dias-etal-2026-sinmix2mono
%X Code-mixed and Romanized texts are widely used in digital content, yet they remain largely underexplored for many low-resource languages, including Sinhala. The scarcity of high-quality parallel data has limited progress on downstream tasks, such as machine translation and transliteration. We introduce SinMix2Mono, the largest manually annotated parallel training dataset, followed by the first gold standard benchmark and code-mixed transliteration ambiguity corpora for code-mixed romanized Sinhala to Sinhala conversion. The dataset comprises approximately 25,000 real-world sentences collected from social media, covering diverse domains and authentic code-mixing patterns. To ensure high-quality translations, we used an annotation pipeline that combined rule-based transliteration, LLM-assisted translation, and human validation. The golden test dataset, which includes 2549 sentences, and the code-mixed transliteration ambiguity test were validated by three annotators, yielding Gwet’s AC1 scores of 0.7465 and 0.7068, respectively. We benchmarked nine systems, including statistical, neural and commercial LLMs. SinMix2Mono provides a robust training and evaluation resource, establishing a strong benchmark for future research on Sinhala code-mixed translation and transliteration.
%U https://aclanthology.org/2026.eamt-1.10/
%P 114-129
Markdown (Informal)
[SinMix2Mono: A Dataset for Code-mixed Romanized Sinhala Translation and Transliteration](https://aclanthology.org/2026.eamt-1.10/) (Dias et al., EAMT 2026)
ACL