@inproceedings{gupta-etal-2025-iitr,
title = "{IITR}-{CIOL}@{NLU} of {D}evanagari Script Languages 2025: Multilingual Hate Speech Detection and Target Identification in {D}evanagari-Scripted Languages",
author = "Gupta, Siddhant and
Singhal, Siddh and
Wasi, Azmine Toushik",
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-1.33/",
pages = "295--300",
abstract = "This work focuses on two subtasks related to hate speech detection and target identification in Devanagari-scripted languages, specifically Hindi, Marathi, Nepali, Bhojpuri, and Sanskrit. Subtask B involves detecting hate speech in online text, while Subtask C requires identifying the specific targets of hate speech, such as individuals, organizations, or communities. We develop a deep neural network built on the pretrained multilingual transformer model {\textquoteleft}ia-multilingual-transliterated-roberta' by IBM, optimized for classification tasks in multilingual and transliterated contexts. The model leverages contextualized embeddings to handle linguistic diversity, with a classifier head for binary classification. We received 88.40{\%} accuracy in Subtask B and 66.11{\%} accuracy in Subtask C, in the test set."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2025-iitr">
<titleInfo>
<title>IITR-CIOL@NLU of Devanagari Script Languages 2025: Multilingual Hate Speech Detection and Target Identification in Devanagari-Scripted Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siddhant</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddh</namePart>
<namePart type="family">Singhal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azmine</namePart>
<namePart type="given">Toushik</namePart>
<namePart type="family">Wasi</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 work focuses on two subtasks related to hate speech detection and target identification in Devanagari-scripted languages, specifically Hindi, Marathi, Nepali, Bhojpuri, and Sanskrit. Subtask B involves detecting hate speech in online text, while Subtask C requires identifying the specific targets of hate speech, such as individuals, organizations, or communities. We develop a deep neural network built on the pretrained multilingual transformer model ‘ia-multilingual-transliterated-roberta’ by IBM, optimized for classification tasks in multilingual and transliterated contexts. The model leverages contextualized embeddings to handle linguistic diversity, with a classifier head for binary classification. We received 88.40% accuracy in Subtask B and 66.11% accuracy in Subtask C, in the test set.</abstract>
<identifier type="citekey">gupta-etal-2025-iitr</identifier>
<location>
<url>https://aclanthology.org/2025.chipsal-1.33/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>295</start>
<end>300</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IITR-CIOL@NLU of Devanagari Script Languages 2025: Multilingual Hate Speech Detection and Target Identification in Devanagari-Scripted Languages
%A Gupta, Siddhant
%A Singhal, Siddh
%A Wasi, Azmine Toushik
%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 gupta-etal-2025-iitr
%X This work focuses on two subtasks related to hate speech detection and target identification in Devanagari-scripted languages, specifically Hindi, Marathi, Nepali, Bhojpuri, and Sanskrit. Subtask B involves detecting hate speech in online text, while Subtask C requires identifying the specific targets of hate speech, such as individuals, organizations, or communities. We develop a deep neural network built on the pretrained multilingual transformer model ‘ia-multilingual-transliterated-roberta’ by IBM, optimized for classification tasks in multilingual and transliterated contexts. The model leverages contextualized embeddings to handle linguistic diversity, with a classifier head for binary classification. We received 88.40% accuracy in Subtask B and 66.11% accuracy in Subtask C, in the test set.
%U https://aclanthology.org/2025.chipsal-1.33/
%P 295-300
Markdown (Informal)
[IITR-CIOL@NLU of Devanagari Script Languages 2025: Multilingual Hate Speech Detection and Target Identification in Devanagari-Scripted Languages](https://aclanthology.org/2025.chipsal-1.33/) (Gupta et al., CHiPSAL 2025)
ACL