@inproceedings{reddy-etal-2024-ssn-nova,
title = "{SSN}-Nova@{LT}-{EDI} 2024: {POS} Tagging, Boosting Techniques and Voting Classifiers for Caste And Migration Hate Speech Detection",
author = "Reddy, A and
Thomas, Ann and
Moorthi, Pranav and
B, Bharathi",
editor = {Chakravarthi, Bharathi Raja and
B, Bharathi and
Buitelaar, Paul and
Durairaj, Thenmozhi and
Kov{\'a}cs, Gy{\"o}rgy and
Garc{\'\i}a Cumbreras, Miguel {\'A}ngel},
booktitle = "Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion",
month = mar,
year = "2024",
address = "St. Julian's, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.ltedi-1.29",
pages = "233--237",
abstract = "This paper presents our submission for the shared task on Caste and Migration Hate Speech Detection: LT-EDI@EACL 20241 . This text classification task aims to foster the creation of models capable of identifying hate speech related to caste and migration. The dataset comprises social media comments, and the goal is to categorize them into negative and positive sentiments. Our approach explores back-translation for data augmentation to address sparse datasets in low-resource Dravidian languages. While Part-of-Speech (POS) tagging is valuable in natural language processing, our work highlights its ineffectiveness in Dravidian languages, with model performance drastically reducing from 0.73 to 0.67 on application. In analyzing boosting and ensemble methods, the voting classifier with traditional models outperforms others and the boosting techniques, underscoring the efficacy of simper models on low-resource data despite augmentation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reddy-etal-2024-ssn-nova">
<titleInfo>
<title>SSN-Nova@LT-EDI 2024: POS Tagging, Boosting Techniques and Voting Classifiers for Caste And Migration Hate Speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Thomas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranav</namePart>
<namePart type="family">Moorthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="family">B</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 Language Technology for Equality, Diversity, Inclusion</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">Bharathi</namePart>
<namePart type="family">B</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Buitelaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thenmozhi</namePart>
<namePart type="family">Durairaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">György</namePart>
<namePart type="family">Kovács</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="given">Ángel</namePart>
<namePart type="family">García Cumbreras</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 presents our submission for the shared task on Caste and Migration Hate Speech Detection: LT-EDI@EACL 20241 . This text classification task aims to foster the creation of models capable of identifying hate speech related to caste and migration. The dataset comprises social media comments, and the goal is to categorize them into negative and positive sentiments. Our approach explores back-translation for data augmentation to address sparse datasets in low-resource Dravidian languages. While Part-of-Speech (POS) tagging is valuable in natural language processing, our work highlights its ineffectiveness in Dravidian languages, with model performance drastically reducing from 0.73 to 0.67 on application. In analyzing boosting and ensemble methods, the voting classifier with traditional models outperforms others and the boosting techniques, underscoring the efficacy of simper models on low-resource data despite augmentation.</abstract>
<identifier type="citekey">reddy-etal-2024-ssn-nova</identifier>
<location>
<url>https://aclanthology.org/2024.ltedi-1.29</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>233</start>
<end>237</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SSN-Nova@LT-EDI 2024: POS Tagging, Boosting Techniques and Voting Classifiers for Caste And Migration Hate Speech Detection
%A Reddy, A.
%A Thomas, Ann
%A Moorthi, Pranav
%A B, Bharathi
%Y Chakravarthi, Bharathi Raja
%Y B, Bharathi
%Y Buitelaar, Paul
%Y Durairaj, Thenmozhi
%Y Kovács, György
%Y García Cumbreras, Miguel Ángel
%S Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F reddy-etal-2024-ssn-nova
%X This paper presents our submission for the shared task on Caste and Migration Hate Speech Detection: LT-EDI@EACL 20241 . This text classification task aims to foster the creation of models capable of identifying hate speech related to caste and migration. The dataset comprises social media comments, and the goal is to categorize them into negative and positive sentiments. Our approach explores back-translation for data augmentation to address sparse datasets in low-resource Dravidian languages. While Part-of-Speech (POS) tagging is valuable in natural language processing, our work highlights its ineffectiveness in Dravidian languages, with model performance drastically reducing from 0.73 to 0.67 on application. In analyzing boosting and ensemble methods, the voting classifier with traditional models outperforms others and the boosting techniques, underscoring the efficacy of simper models on low-resource data despite augmentation.
%U https://aclanthology.org/2024.ltedi-1.29
%P 233-237
Markdown (Informal)
[SSN-Nova@LT-EDI 2024: POS Tagging, Boosting Techniques and Voting Classifiers for Caste And Migration Hate Speech Detection](https://aclanthology.org/2024.ltedi-1.29) (Reddy et al., LTEDI-WS 2024)
ACL