@inproceedings{kumar-etal-2025-team,
title = "Team {I}ndi{D}ata{M}iner at {I}ndo{NLP} 2025: {H}indi Back Transliteration - {R}oman to {D}evanagari using {LL}a{M}a",
author = "Kumar, Saurabh and
Kakadiya, Dhruvkumar Babubhai and
Singh, Sanasam Ranbir",
editor = "Weerasinghe, Ruvan and
Anuradha, Isuri and
Sumanathilaka, Deshan",
booktitle = "Proceedings of the First Workshop on Natural Language Processing for Indo-Aryan and Dravidian Languages",
month = jan,
year = "2025",
address = "Abu Dhabi",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.indonlp-1.15/",
pages = "129--134",
abstract = "The increasing use of Romanized typing for Indo-Aryan languages on social media poses challenges due to its lack of standardization and loss of linguistic richness. To address this, we propose a sentence-level back-transliteration approach using the LLaMa 3.1 model for Hindi. Leveraging fine-tuning with the Dakshina dataset, our approach effectively resolves ambiguities in Romanized Hindi text, offering a robust solution for converting it into the native Devanagari script."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2025-team">
<titleInfo>
<title>Team IndiDataMiner at IndoNLP 2025: Hindi Back Transliteration - Roman to Devanagari using LLaMa</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saurabh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhruvkumar</namePart>
<namePart type="given">Babubhai</namePart>
<namePart type="family">Kakadiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanasam</namePart>
<namePart type="given">Ranbir</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Natural Language Processing for Indo-Aryan and Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruvan</namePart>
<namePart type="family">Weerasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isuri</namePart>
<namePart type="family">Anuradha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deshan</namePart>
<namePart type="family">Sumanathilaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The increasing use of Romanized typing for Indo-Aryan languages on social media poses challenges due to its lack of standardization and loss of linguistic richness. To address this, we propose a sentence-level back-transliteration approach using the LLaMa 3.1 model for Hindi. Leveraging fine-tuning with the Dakshina dataset, our approach effectively resolves ambiguities in Romanized Hindi text, offering a robust solution for converting it into the native Devanagari script.</abstract>
<identifier type="citekey">kumar-etal-2025-team</identifier>
<location>
<url>https://aclanthology.org/2025.indonlp-1.15/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>129</start>
<end>134</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team IndiDataMiner at IndoNLP 2025: Hindi Back Transliteration - Roman to Devanagari using LLaMa
%A Kumar, Saurabh
%A Kakadiya, Dhruvkumar Babubhai
%A Singh, Sanasam Ranbir
%Y Weerasinghe, Ruvan
%Y Anuradha, Isuri
%Y Sumanathilaka, Deshan
%S Proceedings of the First Workshop on Natural Language Processing for Indo-Aryan and Dravidian Languages
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi
%F kumar-etal-2025-team
%X The increasing use of Romanized typing for Indo-Aryan languages on social media poses challenges due to its lack of standardization and loss of linguistic richness. To address this, we propose a sentence-level back-transliteration approach using the LLaMa 3.1 model for Hindi. Leveraging fine-tuning with the Dakshina dataset, our approach effectively resolves ambiguities in Romanized Hindi text, offering a robust solution for converting it into the native Devanagari script.
%U https://aclanthology.org/2025.indonlp-1.15/
%P 129-134
Markdown (Informal)
[Team IndiDataMiner at IndoNLP 2025: Hindi Back Transliteration - Roman to Devanagari using LLaMa](https://aclanthology.org/2025.indonlp-1.15/) (Kumar et al., IndoNLP 2025)
ACL