@inproceedings{kodali-manukonda-2024-bytesizedllm,
title = "byte{S}ized{LLM}@{D}ravidian{L}ang{T}ech 2024: Fake News Detection in {D}ravidian Languages - Unleashing the Power of Custom Subword Tokenization with {S}ubword2{V}ec and {B}i{LSTM}",
author = "Kodali, Rohith and
Manukonda, Durga",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Thavareesan, Sajeetha and
Sherly, Elizabeth and
Nadarajan, Rajeswari and
Ravikiran, Manikandan",
booktitle = "Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages",
month = mar,
year = "2024",
address = "St. Julian's, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.dravidianlangtech-1.12",
pages = "79--84",
abstract = "This paper focuses on detecting fake news in resource-constrained languages, particularly Malayalam. We present a novel framework combining subword tokenization, Sanskrit-transliterated Subword2vec embeddings, and a powerful Bidirectional Long Short-Term Memory (BiLSTM) architecture. Despite using only monolingual Malayalam data, our model excelled in the FakeDetect-Malayalam challenge, ranking 4th. The innovative subword tokenizer achieves a remarkable 200x compression ratio, highlighting its efficiency in minimizing model size without compromising accuracy. Our work facilitates resource-efficient deployment in diverse linguistic landscapes and sparks discussion on the potential of multilingual data augmentation. This research provides a promising avenue for mitigating linguistic challenges in the NLP-driven battle against deceptive content.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kodali-manukonda-2024-bytesizedllm">
<titleInfo>
<title>byteSizedLLM@DravidianLangTech 2024: Fake News Detection in Dravidian Languages - Unleashing the Power of Custom Subword Tokenization with Subword2Vec and BiLSTM</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rohith</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="family">Manukonda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth 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">Rajeswari</namePart>
<namePart type="family">Nadarajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manikandan</namePart>
<namePart type="family">Ravikiran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper focuses on detecting fake news in resource-constrained languages, particularly Malayalam. We present a novel framework combining subword tokenization, Sanskrit-transliterated Subword2vec embeddings, and a powerful Bidirectional Long Short-Term Memory (BiLSTM) architecture. Despite using only monolingual Malayalam data, our model excelled in the FakeDetect-Malayalam challenge, ranking 4th. The innovative subword tokenizer achieves a remarkable 200x compression ratio, highlighting its efficiency in minimizing model size without compromising accuracy. Our work facilitates resource-efficient deployment in diverse linguistic landscapes and sparks discussion on the potential of multilingual data augmentation. This research provides a promising avenue for mitigating linguistic challenges in the NLP-driven battle against deceptive content.</abstract>
<identifier type="citekey">kodali-manukonda-2024-bytesizedllm</identifier>
<location>
<url>https://aclanthology.org/2024.dravidianlangtech-1.12</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>79</start>
<end>84</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T byteSizedLLM@DravidianLangTech 2024: Fake News Detection in Dravidian Languages - Unleashing the Power of Custom Subword Tokenization with Subword2Vec and BiLSTM
%A Kodali, Rohith
%A Manukonda, Durga
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Sherly, Elizabeth
%Y Nadarajan, Rajeswari
%Y Ravikiran, Manikandan
%S Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F kodali-manukonda-2024-bytesizedllm
%X This paper focuses on detecting fake news in resource-constrained languages, particularly Malayalam. We present a novel framework combining subword tokenization, Sanskrit-transliterated Subword2vec embeddings, and a powerful Bidirectional Long Short-Term Memory (BiLSTM) architecture. Despite using only monolingual Malayalam data, our model excelled in the FakeDetect-Malayalam challenge, ranking 4th. The innovative subword tokenizer achieves a remarkable 200x compression ratio, highlighting its efficiency in minimizing model size without compromising accuracy. Our work facilitates resource-efficient deployment in diverse linguistic landscapes and sparks discussion on the potential of multilingual data augmentation. This research provides a promising avenue for mitigating linguistic challenges in the NLP-driven battle against deceptive content.
%U https://aclanthology.org/2024.dravidianlangtech-1.12
%P 79-84
Markdown (Informal)
[byteSizedLLM@DravidianLangTech 2024: Fake News Detection in Dravidian Languages - Unleashing the Power of Custom Subword Tokenization with Subword2Vec and BiLSTM](https://aclanthology.org/2024.dravidianlangtech-1.12) (Kodali & Manukonda, DravidianLangTech-WS 2024)
ACL