@inproceedings{tushi-etal-2025-girlsteam,
title = "girlsteam@{LT}-{EDI}-2025: Caste/Migration based hate speech Detection",
author = "Tushi, Towshin Hossain and
Alam, Walisa and
Ilman, Rehenuma and
Rahman, Samia",
editor = "Gkirtzou, Katerina and
{\v{Z}}itnik, Slavko and
Gracia, Jorge and
Gromann, Dagmar and
di Buono, Maria Pia and
Monti, Johanna and
Ionov, Maxim",
booktitle = "Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion",
month = sep,
year = "2025",
address = "Naples, Italy",
publisher = "Unior Press",
url = "https://aclanthology.org/2025.ltedi-1.29/",
pages = "178--183",
ISBN = "978-88-6719-334-9",
abstract = "The proliferation of caste- and migration-based hate speech on social media poses a significant challenge, particularly in low-resource languages like Tamil. This paper presents our approach to the LT-EDI@ACL 2025 shared task, addressing this issue through a hybrid transformer-based framework. We explore a range of Machine Learning (ML), Deep Learning (DL), and multilingual transformer models, culminating in a novel m-BERT+BiLSTM hybrid architecture. This model integrates contextual embeddings from m-BERT with lexical features from TF-IDF and FastText, feeding the enriched representations into a BiLSTM to capture bidirectional semantic dependencies. Empirical results demonstrate the superiority of this hybrid architecture, achieving a macro-F1 score of 0.76 on the test set and surpassing the performance of standalone models such as MuRIL and IndicBERT. These results affirm the effectiveness of hybrid multilingual models for hate speech detection in low-resource and culturally complex linguistic settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tushi-etal-2025-girlsteam">
<titleInfo>
<title>girlsteam@LT-EDI-2025: Caste/Migration based hate speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Towshin</namePart>
<namePart type="given">Hossain</namePart>
<namePart type="family">Tushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walisa</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rehenuma</namePart>
<namePart type="family">Ilman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Gkirtzou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slavko</namePart>
<namePart type="family">Žitnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Gracia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dagmar</namePart>
<namePart type="family">Gromann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Pia</namePart>
<namePart type="family">di Buono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Monti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxim</namePart>
<namePart type="family">Ionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Unior Press</publisher>
<place>
<placeTerm type="text">Naples, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-88-6719-334-9</identifier>
</relatedItem>
<abstract>The proliferation of caste- and migration-based hate speech on social media poses a significant challenge, particularly in low-resource languages like Tamil. This paper presents our approach to the LT-EDI@ACL 2025 shared task, addressing this issue through a hybrid transformer-based framework. We explore a range of Machine Learning (ML), Deep Learning (DL), and multilingual transformer models, culminating in a novel m-BERT+BiLSTM hybrid architecture. This model integrates contextual embeddings from m-BERT with lexical features from TF-IDF and FastText, feeding the enriched representations into a BiLSTM to capture bidirectional semantic dependencies. Empirical results demonstrate the superiority of this hybrid architecture, achieving a macro-F1 score of 0.76 on the test set and surpassing the performance of standalone models such as MuRIL and IndicBERT. These results affirm the effectiveness of hybrid multilingual models for hate speech detection in low-resource and culturally complex linguistic settings.</abstract>
<identifier type="citekey">tushi-etal-2025-girlsteam</identifier>
<location>
<url>https://aclanthology.org/2025.ltedi-1.29/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>178</start>
<end>183</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T girlsteam@LT-EDI-2025: Caste/Migration based hate speech Detection
%A Tushi, Towshin Hossain
%A Alam, Walisa
%A Ilman, Rehenuma
%A Rahman, Samia
%Y Gkirtzou, Katerina
%Y Žitnik, Slavko
%Y Gracia, Jorge
%Y Gromann, Dagmar
%Y di Buono, Maria Pia
%Y Monti, Johanna
%Y Ionov, Maxim
%S Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion
%D 2025
%8 September
%I Unior Press
%C Naples, Italy
%@ 978-88-6719-334-9
%F tushi-etal-2025-girlsteam
%X The proliferation of caste- and migration-based hate speech on social media poses a significant challenge, particularly in low-resource languages like Tamil. This paper presents our approach to the LT-EDI@ACL 2025 shared task, addressing this issue through a hybrid transformer-based framework. We explore a range of Machine Learning (ML), Deep Learning (DL), and multilingual transformer models, culminating in a novel m-BERT+BiLSTM hybrid architecture. This model integrates contextual embeddings from m-BERT with lexical features from TF-IDF and FastText, feeding the enriched representations into a BiLSTM to capture bidirectional semantic dependencies. Empirical results demonstrate the superiority of this hybrid architecture, achieving a macro-F1 score of 0.76 on the test set and surpassing the performance of standalone models such as MuRIL and IndicBERT. These results affirm the effectiveness of hybrid multilingual models for hate speech detection in low-resource and culturally complex linguistic settings.
%U https://aclanthology.org/2025.ltedi-1.29/
%P 178-183
Markdown (Informal)
[girlsteam@LT-EDI-2025: Caste/Migration based hate speech Detection](https://aclanthology.org/2025.ltedi-1.29/) (Tushi et al., LTEDI 2025)
ACL
- Towshin Hossain Tushi, Walisa Alam, Rehenuma Ilman, and Samia Rahman. 2025. girlsteam@LT-EDI-2025: Caste/Migration based hate speech Detection. In Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion, pages 178–183, Naples, Italy. Unior Press.