@inproceedings{kodali-etal-2025-bytesizedllm,
title = "byte{S}ized{LLM}@{NLU} of {D}evanagari Script Languages 2025: Hate Speech Detection and Target Identification Using Customized Attention {B}i{LSTM} and {XLM}-{R}o{BERT}a Base Embeddings",
author = "Kodali, Rohith Gowtham and
Manukonda, Durga Prasad and
Iglesias, Daniel",
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-1.25/",
pages = "242--247",
abstract = "This paper presents a novel approach to hate speech detection and target identification across Devanagari-script languages, with a focus on Hindi and Nepali. Leveraging an Attention BiLSTM-XLM-RoBERTa architecture, our model effectively captures language-specific features and sequential dependencies crucial for multilingual natural language understanding (NLU). In Task B (Hate Speech Detection), our model achieved a Macro F1 score of 0.7481, demonstrating its robustness in identifying hateful content across linguistic variations. For Task C (Target Identification), it reached a Macro F1 score of 0.6715, highlighting its ability to classify targets into {\textquotedblleft}individual,{\textquotedblright} {\textquotedblleft}organization,{\textquotedblright} and {\textquotedblleft}community{\textquotedblright} with high accuracy. Our work addresses the gap in Devanagari-scripted multilingual hate speech analysis and sets a benchmark for future research in low-resource language contexts."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kodali-etal-2025-bytesizedllm">
<titleInfo>
<title>byteSizedLLM@NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification Using Customized Attention BiLSTM and XLM-RoBERTa Base Embeddings</title>
</titleInfo>
<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>
<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">Daniel</namePart>
<namePart type="family">Iglesias</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 paper presents a novel approach to hate speech detection and target identification across Devanagari-script languages, with a focus on Hindi and Nepali. Leveraging an Attention BiLSTM-XLM-RoBERTa architecture, our model effectively captures language-specific features and sequential dependencies crucial for multilingual natural language understanding (NLU). In Task B (Hate Speech Detection), our model achieved a Macro F1 score of 0.7481, demonstrating its robustness in identifying hateful content across linguistic variations. For Task C (Target Identification), it reached a Macro F1 score of 0.6715, highlighting its ability to classify targets into “individual,” “organization,” and “community” with high accuracy. Our work addresses the gap in Devanagari-scripted multilingual hate speech analysis and sets a benchmark for future research in low-resource language contexts.</abstract>
<identifier type="citekey">kodali-etal-2025-bytesizedllm</identifier>
<location>
<url>https://aclanthology.org/2025.chipsal-1.25/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>242</start>
<end>247</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T byteSizedLLM@NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification Using Customized Attention BiLSTM and XLM-RoBERTa Base Embeddings
%A Kodali, Rohith Gowtham
%A Manukonda, Durga Prasad
%A Iglesias, Daniel
%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 kodali-etal-2025-bytesizedllm
%X This paper presents a novel approach to hate speech detection and target identification across Devanagari-script languages, with a focus on Hindi and Nepali. Leveraging an Attention BiLSTM-XLM-RoBERTa architecture, our model effectively captures language-specific features and sequential dependencies crucial for multilingual natural language understanding (NLU). In Task B (Hate Speech Detection), our model achieved a Macro F1 score of 0.7481, demonstrating its robustness in identifying hateful content across linguistic variations. For Task C (Target Identification), it reached a Macro F1 score of 0.6715, highlighting its ability to classify targets into “individual,” “organization,” and “community” with high accuracy. Our work addresses the gap in Devanagari-scripted multilingual hate speech analysis and sets a benchmark for future research in low-resource language contexts.
%U https://aclanthology.org/2025.chipsal-1.25/
%P 242-247
Markdown (Informal)
[byteSizedLLM@NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification Using Customized Attention BiLSTM and XLM-RoBERTa Base Embeddings](https://aclanthology.org/2025.chipsal-1.25/) (Kodali et al., CHiPSAL 2025)
ACL