@inproceedings{ale-etal-2025-mdsbots,
title = "{MDSB}ots@{NLU} of {D}evanagari Script Languages 2025: Detection of Language, Hate Speech, and Targets using {MURT}weet",
author = "Ale, Prabhat and
Thapaliya, Anish and
Paudel, Suman",
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-1.35/",
pages = "308--313",
abstract = "In multilingual contexts, an automated system for accurate language identification, followed by hate speech detection and target identification, plays a critical role in processing low-resource hate speech data and mitigating its negative impact. This paper presents our approach to the three subtasks in the Shared Task on Natural Language Understanding of Devanagari Script Languages at CHIPSAL@COLING 2025: (i) Language Identification, (ii) Hate Speech Detection, and (iii) Target Identification. Both classical machine learning and multilingual transformer models were explored, where MuRIL Large, trained on undersampled data for subtasks A and B outperformed the classical models. For subtask C, the Hybrid model trained on augmented data achieved superior performance over classical and transformer-based approaches. The top-performing models, named MURTweet for subtasks A and B and NER-MURTweet for subtask C, secured sixth, third, and first rank respectively, in the competition."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ale-etal-2025-mdsbots">
<titleInfo>
<title>MDSBots@NLU of Devanagari Script Languages 2025: Detection of Language, Hate Speech, and Targets using MURTweet</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prabhat</namePart>
<namePart type="family">Ale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anish</namePart>
<namePart type="family">Thapaliya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suman</namePart>
<namePart type="family">Paudel</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>In multilingual contexts, an automated system for accurate language identification, followed by hate speech detection and target identification, plays a critical role in processing low-resource hate speech data and mitigating its negative impact. This paper presents our approach to the three subtasks in the Shared Task on Natural Language Understanding of Devanagari Script Languages at CHIPSAL@COLING 2025: (i) Language Identification, (ii) Hate Speech Detection, and (iii) Target Identification. Both classical machine learning and multilingual transformer models were explored, where MuRIL Large, trained on undersampled data for subtasks A and B outperformed the classical models. For subtask C, the Hybrid model trained on augmented data achieved superior performance over classical and transformer-based approaches. The top-performing models, named MURTweet for subtasks A and B and NER-MURTweet for subtask C, secured sixth, third, and first rank respectively, in the competition.</abstract>
<identifier type="citekey">ale-etal-2025-mdsbots</identifier>
<location>
<url>https://aclanthology.org/2025.chipsal-1.35/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>308</start>
<end>313</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MDSBots@NLU of Devanagari Script Languages 2025: Detection of Language, Hate Speech, and Targets using MURTweet
%A Ale, Prabhat
%A Thapaliya, Anish
%A Paudel, Suman
%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 ale-etal-2025-mdsbots
%X In multilingual contexts, an automated system for accurate language identification, followed by hate speech detection and target identification, plays a critical role in processing low-resource hate speech data and mitigating its negative impact. This paper presents our approach to the three subtasks in the Shared Task on Natural Language Understanding of Devanagari Script Languages at CHIPSAL@COLING 2025: (i) Language Identification, (ii) Hate Speech Detection, and (iii) Target Identification. Both classical machine learning and multilingual transformer models were explored, where MuRIL Large, trained on undersampled data for subtasks A and B outperformed the classical models. For subtask C, the Hybrid model trained on augmented data achieved superior performance over classical and transformer-based approaches. The top-performing models, named MURTweet for subtasks A and B and NER-MURTweet for subtask C, secured sixth, third, and first rank respectively, in the competition.
%U https://aclanthology.org/2025.chipsal-1.35/
%P 308-313
Markdown (Informal)
[MDSBots@NLU of Devanagari Script Languages 2025: Detection of Language, Hate Speech, and Targets using MURTweet](https://aclanthology.org/2025.chipsal-1.35/) (Ale et al., CHiPSAL 2025)
ACL