@inproceedings{pannerselvam-etal-2024-setfit,
title = "{S}et{F}it: A Robust Approach for Offensive Content Detection in {T}amil-{E}nglish Code-Mixed Conversations Using Sentence Transfer Fine-tuning",
author = "Pannerselvam, Kathiravan and
Rajiakodi, Saranya and
Thavareesan, Sajeetha and
Thangasamy, Sathiyaraj and
Ponnusamy, Kishore",
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-1.6",
pages = "35--42",
abstract = "Code-mixed languages are increasingly prevalent on social media and online platforms, presenting significant challenges in offensive content detection for natural language processing (NLP) systems. Our study explores how effectively the Sentence Transfer Fine-tuning (Set-Fit) method, combined with logistic regression, detects offensive content in a Tamil-English code-mixed dataset. We compare our model{'}s performance with five other NLP models: Multilingual BERT (mBERT), LSTM, BERT, IndicBERT, and Language-agnostic BERT Sentence Embeddings (LaBSE). Our model, SetFit, outperforms these models in accuracy, achieving an impressive 89.72{\%}, significantly higher than other models. These results suggest the sentence transformer model{'}s substantial potential for detecting offensive content in codemixed languages. Our study provides valuable insights into the sentence transformer model{'}s ability to identify various types of offensive material in Tamil-English online conversations, paving the way for more advanced NLP systems tailored to code-mixed languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pannerselvam-etal-2024-setfit">
<titleInfo>
<title>SetFit: A Robust Approach for Offensive Content Detection in Tamil-English Code-Mixed Conversations Using Sentence Transfer Fine-tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kathiravan</namePart>
<namePart type="family">Pannerselvam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saranya</namePart>
<namePart type="family">Rajiakodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajeetha</namePart>
<namePart type="family">Thavareesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sathiyaraj</namePart>
<namePart type="family">Thangasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kishore</namePart>
<namePart type="family">Ponnusamy</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>Code-mixed languages are increasingly prevalent on social media and online platforms, presenting significant challenges in offensive content detection for natural language processing (NLP) systems. Our study explores how effectively the Sentence Transfer Fine-tuning (Set-Fit) method, combined with logistic regression, detects offensive content in a Tamil-English code-mixed dataset. We compare our model’s performance with five other NLP models: Multilingual BERT (mBERT), LSTM, BERT, IndicBERT, and Language-agnostic BERT Sentence Embeddings (LaBSE). Our model, SetFit, outperforms these models in accuracy, achieving an impressive 89.72%, significantly higher than other models. These results suggest the sentence transformer model’s substantial potential for detecting offensive content in codemixed languages. Our study provides valuable insights into the sentence transformer model’s ability to identify various types of offensive material in Tamil-English online conversations, paving the way for more advanced NLP systems tailored to code-mixed languages.</abstract>
<identifier type="citekey">pannerselvam-etal-2024-setfit</identifier>
<location>
<url>https://aclanthology.org/2024.dravidianlangtech-1.6</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>35</start>
<end>42</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SetFit: A Robust Approach for Offensive Content Detection in Tamil-English Code-Mixed Conversations Using Sentence Transfer Fine-tuning
%A Pannerselvam, Kathiravan
%A Rajiakodi, Saranya
%A Thavareesan, Sajeetha
%A Thangasamy, Sathiyaraj
%A Ponnusamy, Kishore
%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 pannerselvam-etal-2024-setfit
%X Code-mixed languages are increasingly prevalent on social media and online platforms, presenting significant challenges in offensive content detection for natural language processing (NLP) systems. Our study explores how effectively the Sentence Transfer Fine-tuning (Set-Fit) method, combined with logistic regression, detects offensive content in a Tamil-English code-mixed dataset. We compare our model’s performance with five other NLP models: Multilingual BERT (mBERT), LSTM, BERT, IndicBERT, and Language-agnostic BERT Sentence Embeddings (LaBSE). Our model, SetFit, outperforms these models in accuracy, achieving an impressive 89.72%, significantly higher than other models. These results suggest the sentence transformer model’s substantial potential for detecting offensive content in codemixed languages. Our study provides valuable insights into the sentence transformer model’s ability to identify various types of offensive material in Tamil-English online conversations, paving the way for more advanced NLP systems tailored to code-mixed languages.
%U https://aclanthology.org/2024.dravidianlangtech-1.6
%P 35-42
Markdown (Informal)
[SetFit: A Robust Approach for Offensive Content Detection in Tamil-English Code-Mixed Conversations Using Sentence Transfer Fine-tuning](https://aclanthology.org/2024.dravidianlangtech-1.6) (Pannerselvam et al., DravidianLangTech-WS 2024)
ACL