@inproceedings{chakraborty-etal-2025-one,
title = "One{\_}by{\_}zero@ {NLU} of {D}evanagari Script Languages 2025: Target Identification for Hate Speech Leveraging Transformer-based Approach",
author = "Chakraborty, Dola and
Hossain, Jawad and
Hoque, Mohammed Moshiul",
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-1.38/",
pages = "327--333",
abstract = "People often use written words to spread hate aimed at different groups that cannot be practically detected manually. Therefore, developing an automatic system capable of identifying hate speech is crucial. However, creating such a system in a low-resourced languages (LRLs) script like Devanagari becomes challenging. Hence, the Devanagari script has organized a shared task targeting hate speech identification. This work proposes a pre-trained transformer-based model to identify the target of hate speech, classifying it as directed toward an individual, organization, or community. We performed extensive experiments, exploring various machine learning (LR, SVM, and ensemble), deep learning (CNN, LSTM, CNN+BiLSTM), and transformer-based models (IndicBERT, mBERT, MuRIL, XLM-R) to identify hate speech. Experimental results indicate that the IndicBERT model achieved the highest performance among all other models, obtaining a macro F1-score of 0.6785, which placed the team 6th in the task."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chakraborty-etal-2025-one">
<titleInfo>
<title>One_by_zero@ NLU of Devanagari Script Languages 2025: Target Identification for Hate Speech Leveraging Transformer-based Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dola</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jawad</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Moshiul</namePart>
<namePart type="family">Hoque</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>People often use written words to spread hate aimed at different groups that cannot be practically detected manually. Therefore, developing an automatic system capable of identifying hate speech is crucial. However, creating such a system in a low-resourced languages (LRLs) script like Devanagari becomes challenging. Hence, the Devanagari script has organized a shared task targeting hate speech identification. This work proposes a pre-trained transformer-based model to identify the target of hate speech, classifying it as directed toward an individual, organization, or community. We performed extensive experiments, exploring various machine learning (LR, SVM, and ensemble), deep learning (CNN, LSTM, CNN+BiLSTM), and transformer-based models (IndicBERT, mBERT, MuRIL, XLM-R) to identify hate speech. Experimental results indicate that the IndicBERT model achieved the highest performance among all other models, obtaining a macro F1-score of 0.6785, which placed the team 6th in the task.</abstract>
<identifier type="citekey">chakraborty-etal-2025-one</identifier>
<location>
<url>https://aclanthology.org/2025.chipsal-1.38/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>327</start>
<end>333</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T One_by_zero@ NLU of Devanagari Script Languages 2025: Target Identification for Hate Speech Leveraging Transformer-based Approach
%A Chakraborty, Dola
%A Hossain, Jawad
%A Hoque, Mohammed Moshiul
%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 chakraborty-etal-2025-one
%X People often use written words to spread hate aimed at different groups that cannot be practically detected manually. Therefore, developing an automatic system capable of identifying hate speech is crucial. However, creating such a system in a low-resourced languages (LRLs) script like Devanagari becomes challenging. Hence, the Devanagari script has organized a shared task targeting hate speech identification. This work proposes a pre-trained transformer-based model to identify the target of hate speech, classifying it as directed toward an individual, organization, or community. We performed extensive experiments, exploring various machine learning (LR, SVM, and ensemble), deep learning (CNN, LSTM, CNN+BiLSTM), and transformer-based models (IndicBERT, mBERT, MuRIL, XLM-R) to identify hate speech. Experimental results indicate that the IndicBERT model achieved the highest performance among all other models, obtaining a macro F1-score of 0.6785, which placed the team 6th in the task.
%U https://aclanthology.org/2025.chipsal-1.38/
%P 327-333
Markdown (Informal)
[One_by_zero@ NLU of Devanagari Script Languages 2025: Target Identification for Hate Speech Leveraging Transformer-based Approach](https://aclanthology.org/2025.chipsal-1.38/) (Chakraborty et al., CHiPSAL 2025)
ACL