@inproceedings{kodali-etal-2025-bytesizedllm-dravidianlangtech-2025,
title = "byte{S}ized{LLM}@{D}ravidian{L}ang{T}ech 2025: Abusive {T}amil and {M}alayalam Text targeting Women on Social Media Using {XLM}-{R}o{BERT}a and Attention-{B}i{LSTM}",
author = "Kodali, Rohith Gowtham and
Manukonda, Durga Prasad and
Pannakkaran, Maharajan",
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-1.14/",
doi = "10.18653/v1/2025.dravidianlangtech-1.14",
pages = "80--85",
ISBN = "979-8-89176-228-2",
abstract = "This research investigates abusive comment detection in Tamil and Malayalam, focusing on code-mixed, multilingual social media text. A hybrid Attention BiLSTM-XLM-RoBERTa model was utilized, combining fine-tuned embeddings, sequential dependencies, and attention mechanisms. Despite computational constraints limiting fine-tuning to a subset of the AI4Bharath dataset, the model achieved competitive macro F1-scores, ranking 6th for both Tamil and Malayalam datasets with minor performance differences. The results emphasize the potential of multilingual transformers and the need for further advancements, particularly in addressing linguistic diversity, transliteration complexity, and computational limitations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kodali-etal-2025-bytesizedllm-dravidianlangtech-2025">
<titleInfo>
<title>byteSizedLLM@DravidianLangTech 2025: Abusive Tamil and Malayalam Text targeting Women on Social Media Using XLM-RoBERTa and Attention-BiLSTM</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rohith</namePart>
<namePart type="given">Gowtham</namePart>
<namePart type="family">Kodali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Durga</namePart>
<namePart type="given">Prasad</namePart>
<namePart type="family">Manukonda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maharajan</namePart>
<namePart type="family">Pannakkaran</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 research investigates abusive comment detection in Tamil and Malayalam, focusing on code-mixed, multilingual social media text. A hybrid Attention BiLSTM-XLM-RoBERTa model was utilized, combining fine-tuned embeddings, sequential dependencies, and attention mechanisms. Despite computational constraints limiting fine-tuning to a subset of the AI4Bharath dataset, the model achieved competitive macro F1-scores, ranking 6th for both Tamil and Malayalam datasets with minor performance differences. The results emphasize the potential of multilingual transformers and the need for further advancements, particularly in addressing linguistic diversity, transliteration complexity, and computational limitations.</abstract>
<identifier type="citekey">kodali-etal-2025-bytesizedllm-dravidianlangtech-2025</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.14</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.14/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>80</start>
<end>85</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T byteSizedLLM@DravidianLangTech 2025: Abusive Tamil and Malayalam Text targeting Women on Social Media Using XLM-RoBERTa and Attention-BiLSTM
%A Kodali, Rohith Gowtham
%A Manukonda, Durga Prasad
%A Pannakkaran, Maharajan
%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 kodali-etal-2025-bytesizedllm-dravidianlangtech-2025
%X This research investigates abusive comment detection in Tamil and Malayalam, focusing on code-mixed, multilingual social media text. A hybrid Attention BiLSTM-XLM-RoBERTa model was utilized, combining fine-tuned embeddings, sequential dependencies, and attention mechanisms. Despite computational constraints limiting fine-tuning to a subset of the AI4Bharath dataset, the model achieved competitive macro F1-scores, ranking 6th for both Tamil and Malayalam datasets with minor performance differences. The results emphasize the potential of multilingual transformers and the need for further advancements, particularly in addressing linguistic diversity, transliteration complexity, and computational limitations.
%R 10.18653/v1/2025.dravidianlangtech-1.14
%U https://aclanthology.org/2025.dravidianlangtech-1.14/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.14
%P 80-85
Markdown (Informal)
[byteSizedLLM@DravidianLangTech 2025: Abusive Tamil and Malayalam Text targeting Women on Social Media Using XLM-RoBERTa and Attention-BiLSTM](https://aclanthology.org/2025.dravidianlangtech-1.14/) (Kodali et al., DravidianLangTech 2025)
ACL