@inproceedings{thavarasa-etal-2025-incepto,
title = "Incepto@{D}ravidian{L}ang{T}ech 2025: Detecting Abusive {T}amil and {M}alayalam Text Targeting Women on {Y}ou{T}ube",
author = "Thavarasa, Luxshan and
Sukumar, Sivasuthan and
Thevakumar, Jubeerathan",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Thavareesan, Sajeetha and
Sherly, Elizabeth and
Rajiakodi, Saranya and
Palani, Balasubramanian and
Subramanian, Malliga and
Cn, Subalalitha and
Chinnappa, Dhivya",
booktitle = "Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages",
month = may,
year = "2025",
address = "Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.dravidianlangtech-1.1/",
doi = "10.18653/v1/2025.dravidianlangtech-1.1",
pages = "1--5",
ISBN = "979-8-89176-228-2",
abstract = "This study introduces a novel multilingualmodel designed to effectively address the challenges of detecting abusive content in low resource, code-mixed languages, where limiteddata availability and the interplay of mixed languages, leading to complex linguistic phenomena, create significant hurdles in developingrobust machine learning models. By leveraging transfer learning techniques and employingmulti-head attention mechanisms, our modeldemonstrates impressive performance in detecting abusive content in both Tamil and Malayalam datasets. On the Tamil dataset, our teamachieved a macro F1 score of 0.7864, whilefor the Malayalam dataset, a macro F1 score of0.7058 was attained. These results highlight theeffectiveness of our multilingual approach, delivering strong performance in Tamil and competitive results in Malayalam."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thavarasa-etal-2025-incepto">
<titleInfo>
<title>Incepto@DravidianLangTech 2025: Detecting Abusive Tamil and Malayalam Text Targeting Women on YouTube</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luxshan</namePart>
<namePart type="family">Thavarasa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sivasuthan</namePart>
<namePart type="family">Sukumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jubeerathan</namePart>
<namePart type="family">Thevakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Madasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajeetha</namePart>
<namePart type="family">Thavareesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saranya</namePart>
<namePart type="family">Rajiakodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balasubramanian</namePart>
<namePart type="family">Palani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malliga</namePart>
<namePart type="family">Subramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subalalitha</namePart>
<namePart type="family">Cn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhivya</namePart>
<namePart type="family">Chinnappa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-228-2</identifier>
</relatedItem>
<abstract>This study introduces a novel multilingualmodel designed to effectively address the challenges of detecting abusive content in low resource, code-mixed languages, where limiteddata availability and the interplay of mixed languages, leading to complex linguistic phenomena, create significant hurdles in developingrobust machine learning models. By leveraging transfer learning techniques and employingmulti-head attention mechanisms, our modeldemonstrates impressive performance in detecting abusive content in both Tamil and Malayalam datasets. On the Tamil dataset, our teamachieved a macro F1 score of 0.7864, whilefor the Malayalam dataset, a macro F1 score of0.7058 was attained. These results highlight theeffectiveness of our multilingual approach, delivering strong performance in Tamil and competitive results in Malayalam.</abstract>
<identifier type="citekey">thavarasa-etal-2025-incepto</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.1</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.1/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>1</start>
<end>5</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incepto@DravidianLangTech 2025: Detecting Abusive Tamil and Malayalam Text Targeting Women on YouTube
%A Thavarasa, Luxshan
%A Sukumar, Sivasuthan
%A Thevakumar, Jubeerathan
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Sherly, Elizabeth
%Y Rajiakodi, Saranya
%Y Palani, Balasubramanian
%Y Subramanian, Malliga
%Y Cn, Subalalitha
%Y Chinnappa, Dhivya
%S Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages
%D 2025
%8 May
%I Association for Computational Linguistics
%C Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico
%@ 979-8-89176-228-2
%F thavarasa-etal-2025-incepto
%X This study introduces a novel multilingualmodel designed to effectively address the challenges of detecting abusive content in low resource, code-mixed languages, where limiteddata availability and the interplay of mixed languages, leading to complex linguistic phenomena, create significant hurdles in developingrobust machine learning models. By leveraging transfer learning techniques and employingmulti-head attention mechanisms, our modeldemonstrates impressive performance in detecting abusive content in both Tamil and Malayalam datasets. On the Tamil dataset, our teamachieved a macro F1 score of 0.7864, whilefor the Malayalam dataset, a macro F1 score of0.7058 was attained. These results highlight theeffectiveness of our multilingual approach, delivering strong performance in Tamil and competitive results in Malayalam.
%R 10.18653/v1/2025.dravidianlangtech-1.1
%U https://aclanthology.org/2025.dravidianlangtech-1.1/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.1
%P 1-5
Markdown (Informal)
[Incepto@DravidianLangTech 2025: Detecting Abusive Tamil and Malayalam Text Targeting Women on YouTube](https://aclanthology.org/2025.dravidianlangtech-1.1/) (Thavarasa et al., DravidianLangTech 2025)
ACL