@inproceedings{harini-etal-2025-htms,
title = "{HTMS}@{D}ravidian{L}ang{T}ech 2025: Fusing {TF}-{IDF} and {BERT} with Dimensionality Reduction for Abusive Language Detection in {T}amil and {M}alayalam",
author = "Harini, Bachu Naga Sri and
Meghana, Kankipati Venkata and
Supriya, Kondakindi and
Samiksha, Tara and
B, Premjith",
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-1.25/",
doi = "10.18653/v1/2025.dravidianlangtech-1.25",
pages = "152--156",
ISBN = "979-8-89176-228-2",
abstract = "Detecting abusive and similarly toxic content posted on a social media platform is challenging due to the complexities of the language, data imbalance, and the code-mixed nature of the text. In this paper, we present our submissions for the shared task on abusive Tamil and Malayalam texts targeting women on social media{---}DravidianLangTech@NAACL 2025. We propose a hybrid embedding model that integrates embeddings generated using term frequency-inverse document frequency (TF-IDF) and BERT. To get rid of the differences in the embedding dimensions, we used a dimensionality reduction method with TF-IDF embedding. We submitted two more runs to the shared task, which involve a model based on TF-IDF embedding and another based on BERT-based embedding. The code for the submissions is available at https://github.com/Tarrruh/NLP{\_}HTMS."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="harini-etal-2025-htms">
<titleInfo>
<title>HTMS@DravidianLangTech 2025: Fusing TF-IDF and BERT with Dimensionality Reduction for Abusive Language Detection in Tamil and Malayalam</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bachu</namePart>
<namePart type="given">Naga</namePart>
<namePart type="given">Sri</namePart>
<namePart type="family">Harini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kankipati</namePart>
<namePart type="given">Venkata</namePart>
<namePart type="family">Meghana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kondakindi</namePart>
<namePart type="family">Supriya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tara</namePart>
<namePart type="family">Samiksha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Premjith</namePart>
<namePart type="family">B</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>Detecting abusive and similarly toxic content posted on a social media platform is challenging due to the complexities of the language, data imbalance, and the code-mixed nature of the text. In this paper, we present our submissions for the shared task on abusive Tamil and Malayalam texts targeting women on social media—DravidianLangTech@NAACL 2025. We propose a hybrid embedding model that integrates embeddings generated using term frequency-inverse document frequency (TF-IDF) and BERT. To get rid of the differences in the embedding dimensions, we used a dimensionality reduction method with TF-IDF embedding. We submitted two more runs to the shared task, which involve a model based on TF-IDF embedding and another based on BERT-based embedding. The code for the submissions is available at https://github.com/Tarrruh/NLP_HTMS.</abstract>
<identifier type="citekey">harini-etal-2025-htms</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.25</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.25/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>152</start>
<end>156</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HTMS@DravidianLangTech 2025: Fusing TF-IDF and BERT with Dimensionality Reduction for Abusive Language Detection in Tamil and Malayalam
%A Harini, Bachu Naga Sri
%A Meghana, Kankipati Venkata
%A Supriya, Kondakindi
%A Samiksha, Tara
%A B, Premjith
%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 harini-etal-2025-htms
%X Detecting abusive and similarly toxic content posted on a social media platform is challenging due to the complexities of the language, data imbalance, and the code-mixed nature of the text. In this paper, we present our submissions for the shared task on abusive Tamil and Malayalam texts targeting women on social media—DravidianLangTech@NAACL 2025. We propose a hybrid embedding model that integrates embeddings generated using term frequency-inverse document frequency (TF-IDF) and BERT. To get rid of the differences in the embedding dimensions, we used a dimensionality reduction method with TF-IDF embedding. We submitted two more runs to the shared task, which involve a model based on TF-IDF embedding and another based on BERT-based embedding. The code for the submissions is available at https://github.com/Tarrruh/NLP_HTMS.
%R 10.18653/v1/2025.dravidianlangtech-1.25
%U https://aclanthology.org/2025.dravidianlangtech-1.25/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.25
%P 152-156
Markdown (Informal)
[HTMS@DravidianLangTech 2025: Fusing TF-IDF and BERT with Dimensionality Reduction for Abusive Language Detection in Tamil and Malayalam](https://aclanthology.org/2025.dravidianlangtech-1.25/) (Harini et al., DravidianLangTech 2025)
ACL
- Bachu Naga Sri Harini, Kankipati Venkata Meghana, Kondakindi Supriya, Tara Samiksha, and Premjith B. 2025. HTMS@DravidianLangTech 2025: Fusing TF-IDF and BERT with Dimensionality Reduction for Abusive Language Detection in Tamil and Malayalam. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 152–156, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.