@inproceedings{dias-sumanathilaka-2025-systematic,
title = "A Systematic Review on Machine Translation and Transliteration Techniques for Code-Mixed {I}ndo-{A}ryan Languages",
author = "Dias, H. Rukshan and
Sumanathilaka, Deshan",
editor = "Nakazawa, Toshiaki and
Goto, Isao",
booktitle = "Proceedings of the Twelfth Workshop on Asian Translation (WAT 2025)",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.wat-1.6/",
pages = "66--77",
ISBN = "979-8-89176-309-8",
abstract = "In multilingual societies, it is common to observe the blending of multiple languages in communication, a phenomenon known as $\textbf{Code-mixing}$. Globalization and the increasing influence of social media have further amplified multilingualism, resulting in a wider use of code-mixing. This systematic review analyzes existing translation and transliteration techniques for code-mixed Indo-Aryan languages, spanning rule-based and statistical approaches to neural machine translation and transformer-based architectures. It also examines publicly available code-mixed datasets designed for machine translation and transliteration tasks, along with the evaluation metrics commonly introduced and applied in prior studies. Finally, the paper discusses current challenges and limitations, highlighting future research directions for developing more tailored translation pipelines for code-mixed Indo-Aryan languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dias-sumanathilaka-2025-systematic">
<titleInfo>
<title>A Systematic Review on Machine Translation and Transliteration Techniques for Code-Mixed Indo-Aryan Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">H</namePart>
<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>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Workshop on Asian Translation (WAT 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isao</namePart>
<namePart type="family">Goto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-309-8</identifier>
</relatedItem>
<abstract>In multilingual societies, it is common to observe the blending of multiple languages in communication, a phenomenon known as Code-mixing. Globalization and the increasing influence of social media have further amplified multilingualism, resulting in a wider use of code-mixing. This systematic review analyzes existing translation and transliteration techniques for code-mixed Indo-Aryan languages, spanning rule-based and statistical approaches to neural machine translation and transformer-based architectures. It also examines publicly available code-mixed datasets designed for machine translation and transliteration tasks, along with the evaluation metrics commonly introduced and applied in prior studies. Finally, the paper discusses current challenges and limitations, highlighting future research directions for developing more tailored translation pipelines for code-mixed Indo-Aryan languages.</abstract>
<identifier type="citekey">dias-sumanathilaka-2025-systematic</identifier>
<location>
<url>https://aclanthology.org/2025.wat-1.6/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>66</start>
<end>77</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Systematic Review on Machine Translation and Transliteration Techniques for Code-Mixed Indo-Aryan Languages
%A Dias, H. Rukshan
%A Sumanathilaka, Deshan
%Y Nakazawa, Toshiaki
%Y Goto, Isao
%S Proceedings of the Twelfth Workshop on Asian Translation (WAT 2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-309-8
%F dias-sumanathilaka-2025-systematic
%X In multilingual societies, it is common to observe the blending of multiple languages in communication, a phenomenon known as Code-mixing. Globalization and the increasing influence of social media have further amplified multilingualism, resulting in a wider use of code-mixing. This systematic review analyzes existing translation and transliteration techniques for code-mixed Indo-Aryan languages, spanning rule-based and statistical approaches to neural machine translation and transformer-based architectures. It also examines publicly available code-mixed datasets designed for machine translation and transliteration tasks, along with the evaluation metrics commonly introduced and applied in prior studies. Finally, the paper discusses current challenges and limitations, highlighting future research directions for developing more tailored translation pipelines for code-mixed Indo-Aryan languages.
%U https://aclanthology.org/2025.wat-1.6/
%P 66-77
Markdown (Informal)
[A Systematic Review on Machine Translation and Transliteration Techniques for Code-Mixed Indo-Aryan Languages](https://aclanthology.org/2025.wat-1.6/) (Dias & Sumanathilaka, WAT 2025)
ACL