@inproceedings{chauhan-kumar-2025-dslnlp,
title = "{DSLNLP}@{NLU} of {D}evanagari Script Languages 2025: Leveraging {BERT}-based Architectures for Language Identification, Hate Speech Detection and Target Classification",
author = "Chauhan, Shraddha and
Kumar, Abhinav",
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-1.32/",
pages = "289--294",
abstract = "The rapid rise of social media has emphasized the spread of harmful and hateful content, making it challenging for its identification. Contextual semantics is very important as prior studies present that context level semantics is a more trustworthy indicator of hatefulness than word level semantics for detecting hate speech. This paper attempts to check the usability of transformer-based models for the identification of hate speech on code-mixed datasets, which includes Google-MuRIL, LaBSE, XLMRoberta-base, mbert and distil-mbert. The above is largely due to its ability for high-level representations of complex and context-dense meaning. Besides this, we experiment on ensemble approach that covers all of the above models to reach out for an even higher level of performance in detection. The experiment results show the best performing macro F1-scores are reported in case of MuRIL in comparison to other implemented models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chauhan-kumar-2025-dslnlp">
<titleInfo>
<title>DSLNLP@NLU of Devanagari Script Languages 2025: Leveraging BERT-based Architectures for Language Identification, Hate Speech Detection and Target Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shraddha</namePart>
<namePart type="family">Chauhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Kumar</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>The rapid rise of social media has emphasized the spread of harmful and hateful content, making it challenging for its identification. Contextual semantics is very important as prior studies present that context level semantics is a more trustworthy indicator of hatefulness than word level semantics for detecting hate speech. This paper attempts to check the usability of transformer-based models for the identification of hate speech on code-mixed datasets, which includes Google-MuRIL, LaBSE, XLMRoberta-base, mbert and distil-mbert. The above is largely due to its ability for high-level representations of complex and context-dense meaning. Besides this, we experiment on ensemble approach that covers all of the above models to reach out for an even higher level of performance in detection. The experiment results show the best performing macro F1-scores are reported in case of MuRIL in comparison to other implemented models.</abstract>
<identifier type="citekey">chauhan-kumar-2025-dslnlp</identifier>
<location>
<url>https://aclanthology.org/2025.chipsal-1.32/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>289</start>
<end>294</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DSLNLP@NLU of Devanagari Script Languages 2025: Leveraging BERT-based Architectures for Language Identification, Hate Speech Detection and Target Classification
%A Chauhan, Shraddha
%A Kumar, Abhinav
%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 chauhan-kumar-2025-dslnlp
%X The rapid rise of social media has emphasized the spread of harmful and hateful content, making it challenging for its identification. Contextual semantics is very important as prior studies present that context level semantics is a more trustworthy indicator of hatefulness than word level semantics for detecting hate speech. This paper attempts to check the usability of transformer-based models for the identification of hate speech on code-mixed datasets, which includes Google-MuRIL, LaBSE, XLMRoberta-base, mbert and distil-mbert. The above is largely due to its ability for high-level representations of complex and context-dense meaning. Besides this, we experiment on ensemble approach that covers all of the above models to reach out for an even higher level of performance in detection. The experiment results show the best performing macro F1-scores are reported in case of MuRIL in comparison to other implemented models.
%U https://aclanthology.org/2025.chipsal-1.32/
%P 289-294
Markdown (Informal)
[DSLNLP@NLU of Devanagari Script Languages 2025: Leveraging BERT-based Architectures for Language Identification, Hate Speech Detection and Target Classification](https://aclanthology.org/2025.chipsal-1.32/) (Chauhan & Kumar, CHiPSAL 2025)
ACL