@inproceedings{manukonda-etal-2025-bytesizedllm,
title = "byte{S}ized{LLM}@{D}ravidian{L}ang{T}ech 2025: Multimodal Hate Speech Detection in {M}alayalam Using Attention-Driven {B}i{LSTM}, {M}alayalam-Topic-{BERT}, and Fine-Tuned {W}av2{V}ec 2.0",
author = "Manukonda, Durga Prasad and
Kodali, Rohith Gowtham and
Iglesias, Daniel",
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-1.12/",
doi = "10.18653/v1/2025.dravidianlangtech-1.12",
pages = "68--73",
ISBN = "979-8-89176-228-2",
abstract = "This research presents a robust multimodal framework for hate speech detection in Malayalam, combining fine-tuned Wav2Vec 2.0, Malayalam-Doc-Topic-BERT, and an Attention-Driven BiLSTM architecture. The proposed approach effectively integrates acoustic and textual features, achieving a macro F1-score of 0.84 on the Malayalam test set. Fine-tuning Wav2Vec 2.0 on Malayalam speech data and leveraging Malayalam-Doc-Topic-BERT significantly improved performance over prior methods using openly available models. The results highlight the potential of language-specific models and advanced multimodal fusion techniques for addressing nuanced hate speech categories, setting the stage for future work on Dravidian languages like Tamil and Telugu."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="manukonda-etal-2025-bytesizedllm">
<titleInfo>
<title>byteSizedLLM@DravidianLangTech 2025: Multimodal Hate Speech Detection in Malayalam Using Attention-Driven BiLSTM, Malayalam-Topic-BERT, and Fine-Tuned Wav2Vec 2.0</title>
</titleInfo>
<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">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">Daniel</namePart>
<namePart type="family">Iglesias</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 presents a robust multimodal framework for hate speech detection in Malayalam, combining fine-tuned Wav2Vec 2.0, Malayalam-Doc-Topic-BERT, and an Attention-Driven BiLSTM architecture. The proposed approach effectively integrates acoustic and textual features, achieving a macro F1-score of 0.84 on the Malayalam test set. Fine-tuning Wav2Vec 2.0 on Malayalam speech data and leveraging Malayalam-Doc-Topic-BERT significantly improved performance over prior methods using openly available models. The results highlight the potential of language-specific models and advanced multimodal fusion techniques for addressing nuanced hate speech categories, setting the stage for future work on Dravidian languages like Tamil and Telugu.</abstract>
<identifier type="citekey">manukonda-etal-2025-bytesizedllm</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.12</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.12/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>68</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T byteSizedLLM@DravidianLangTech 2025: Multimodal Hate Speech Detection in Malayalam Using Attention-Driven BiLSTM, Malayalam-Topic-BERT, and Fine-Tuned Wav2Vec 2.0
%A Manukonda, Durga Prasad
%A Kodali, Rohith Gowtham
%A Iglesias, Daniel
%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 manukonda-etal-2025-bytesizedllm
%X This research presents a robust multimodal framework for hate speech detection in Malayalam, combining fine-tuned Wav2Vec 2.0, Malayalam-Doc-Topic-BERT, and an Attention-Driven BiLSTM architecture. The proposed approach effectively integrates acoustic and textual features, achieving a macro F1-score of 0.84 on the Malayalam test set. Fine-tuning Wav2Vec 2.0 on Malayalam speech data and leveraging Malayalam-Doc-Topic-BERT significantly improved performance over prior methods using openly available models. The results highlight the potential of language-specific models and advanced multimodal fusion techniques for addressing nuanced hate speech categories, setting the stage for future work on Dravidian languages like Tamil and Telugu.
%R 10.18653/v1/2025.dravidianlangtech-1.12
%U https://aclanthology.org/2025.dravidianlangtech-1.12/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.12
%P 68-73
Markdown (Informal)
[byteSizedLLM@DravidianLangTech 2025: Multimodal Hate Speech Detection in Malayalam Using Attention-Driven BiLSTM, Malayalam-Topic-BERT, and Fine-Tuned Wav2Vec 2.0](https://aclanthology.org/2025.dravidianlangtech-1.12/) (Manukonda et al., DravidianLangTech 2025)
ACL
- Durga Prasad Manukonda, Rohith Gowtham Kodali, and Daniel Iglesias. 2025. byteSizedLLM@DravidianLangTech 2025: Multimodal Hate Speech Detection in Malayalam Using Attention-Driven BiLSTM, Malayalam-Topic-BERT, and Fine-Tuned Wav2Vec 2.0. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 68–73, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.