@inproceedings{manukonda-kodali-2025-bytesizedllm,
title = "byte{S}ized{LLM}@{NLU} of {D}evanagari Script Languages 2025: Language Identification Using Customized Attention {B}i{LSTM} and {XLM}-{R}o{BERT}a base Embeddings",
author = "Manukonda, Durga Prasad and
Kodali, Rohith Gowtham",
editor = "Sarveswaran, Kengatharaiyer and
Vaidya, Ashwini and
Krishna Bal, Bal and
Shams, Sana and
Thapa, Surendrabikram",
booktitle = "Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2025.chipsal-1.26/",
pages = "248--252",
abstract = "This study explores the challenges of natural language understanding (NLU) in multilingual contexts, focusing on Devanagari-scripted languages such as Nepali, Marathi, Sanskrit, Bhojpuri, and Hindi. Language identification within these languages is complex due to their structural and lexical similarities. We present a hybrid Attention BiLSTM-XLM-RoBERTa model, achieving a state-of-the-art F1 score of 0.9974 on the test set, despite limited resources. Our model effectively distinguishes between closely related Devanagari-scripted languages, providing a solid foundation for context-aware NLU systems that enhance language-specific processing and promote inclusive digital interactions across diverse linguistic communities."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="manukonda-kodali-2025-bytesizedllm">
<titleInfo>
<title>byteSizedLLM@NLU of Devanagari Script Languages 2025: Language Identification Using Customized Attention BiLSTM and XLM-RoBERTa base Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Durga</namePart>
<namePart type="given">Prasad</namePart>
<namePart type="family">Manukonda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohith</namePart>
<namePart type="given">Gowtham</namePart>
<namePart type="family">Kodali</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 Challenges in Processing South Asian Languages (CHiPSAL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kengatharaiyer</namePart>
<namePart type="family">Sarveswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwini</namePart>
<namePart type="family">Vaidya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bal</namePart>
<namePart type="family">Krishna Bal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sana</namePart>
<namePart type="family">Shams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study explores the challenges of natural language understanding (NLU) in multilingual contexts, focusing on Devanagari-scripted languages such as Nepali, Marathi, Sanskrit, Bhojpuri, and Hindi. Language identification within these languages is complex due to their structural and lexical similarities. We present a hybrid Attention BiLSTM-XLM-RoBERTa model, achieving a state-of-the-art F1 score of 0.9974 on the test set, despite limited resources. Our model effectively distinguishes between closely related Devanagari-scripted languages, providing a solid foundation for context-aware NLU systems that enhance language-specific processing and promote inclusive digital interactions across diverse linguistic communities.</abstract>
<identifier type="citekey">manukonda-kodali-2025-bytesizedllm</identifier>
<location>
<url>https://aclanthology.org/2025.chipsal-1.26/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>248</start>
<end>252</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T byteSizedLLM@NLU of Devanagari Script Languages 2025: Language Identification Using Customized Attention BiLSTM and XLM-RoBERTa base Embeddings
%A Manukonda, Durga Prasad
%A Kodali, Rohith Gowtham
%Y Sarveswaran, Kengatharaiyer
%Y Vaidya, Ashwini
%Y Krishna Bal, Bal
%Y Shams, Sana
%Y Thapa, Surendrabikram
%S Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)
%D 2025
%8 January
%I International Committee on Computational Linguistics
%C Abu Dhabi, UAE
%F manukonda-kodali-2025-bytesizedllm
%X This study explores the challenges of natural language understanding (NLU) in multilingual contexts, focusing on Devanagari-scripted languages such as Nepali, Marathi, Sanskrit, Bhojpuri, and Hindi. Language identification within these languages is complex due to their structural and lexical similarities. We present a hybrid Attention BiLSTM-XLM-RoBERTa model, achieving a state-of-the-art F1 score of 0.9974 on the test set, despite limited resources. Our model effectively distinguishes between closely related Devanagari-scripted languages, providing a solid foundation for context-aware NLU systems that enhance language-specific processing and promote inclusive digital interactions across diverse linguistic communities.
%U https://aclanthology.org/2025.chipsal-1.26/
%P 248-252
Markdown (Informal)
[byteSizedLLM@NLU of Devanagari Script Languages 2025: Language Identification Using Customized Attention BiLSTM and XLM-RoBERTa base Embeddings](https://aclanthology.org/2025.chipsal-1.26/) (Manukonda & Kodali, CHiPSAL 2025)
ACL