@inproceedings{hegde-etal-2023-mucs-lt-edi2023,
title = "{MUCS}@{LT}-{EDI}2023: Homophobic/Transphobic Content Detection in Social Media Text using m{BERT}",
author = "Hegde, Asha and
G, Kavya and
Coelho, Sharal and
Shashirekha, Hosahalli Lakshmaiah",
editor = "Chakravarthi, Bharathi R. and
Bharathi, B. and
Griffith, Joephine and
Bali, Kalika and
Buitelaar, Paul",
booktitle = "Proceedings of the Third Workshop on Language Technology for Equality, Diversity and Inclusion",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.ltedi-1.44/",
pages = "287--294",
abstract = "Homophobic/Transphobic (H/T) content includes hate speech, discrimination text, and abusive comments against Gay, Lesbian, Bisexual, Transgender, Queer, and Intersex (LGBTQ) individuals. With the increase in user generated text in social media, there has been an increase in code-mixed H/T content, which poses challenges for efficient analysis and detection of H/T content on social media. The complex nature of code-mixed text necessitates the development of advanced tools and techniques to effectively tackle this issue in social media platforms. To tackle this issue, in this paper, we - team MUCS, describe the transformer based models submitted to {\textquotedblleft}Homophobia/Transphobia Detection in social media comments{\textquotedblright} shared task in Language Technology for Equality, Diversity and Inclusion (LT-EDI) at Recent Advances in Natural Language Processing (RANLP)-2023. The proposed methodology makes use of resampling the training data to handle the data imbalance and this resampled data is used to fine-tune the Multilingual Bidirectional Encoder Representations from Transformers (mBERT) models. These models obtained 11th, 5th, 3rd, 3rd, and 7th ranks for English, Tamil, Malayalam, Spanish, and Hindi respectively in Task A and 8th, 2nd, and 2nd ranks for English, Tamil, and Malayalam respectively in Task B."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hegde-etal-2023-mucs-lt-edi2023">
<titleInfo>
<title>MUCS@LT-EDI2023: Homophobic/Transphobic Content Detection in Social Media Text using mBERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asha</namePart>
<namePart type="family">Hegde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kavya</namePart>
<namePart type="family">G</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharal</namePart>
<namePart type="family">Coelho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosahalli</namePart>
<namePart type="given">Lakshmaiah</namePart>
<namePart type="family">Shashirekha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Language Technology for Equality, Diversity and Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">B</namePart>
<namePart type="family">Bharathi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joephine</namePart>
<namePart type="family">Griffith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</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>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Homophobic/Transphobic (H/T) content includes hate speech, discrimination text, and abusive comments against Gay, Lesbian, Bisexual, Transgender, Queer, and Intersex (LGBTQ) individuals. With the increase in user generated text in social media, there has been an increase in code-mixed H/T content, which poses challenges for efficient analysis and detection of H/T content on social media. The complex nature of code-mixed text necessitates the development of advanced tools and techniques to effectively tackle this issue in social media platforms. To tackle this issue, in this paper, we - team MUCS, describe the transformer based models submitted to “Homophobia/Transphobia Detection in social media comments” shared task in Language Technology for Equality, Diversity and Inclusion (LT-EDI) at Recent Advances in Natural Language Processing (RANLP)-2023. The proposed methodology makes use of resampling the training data to handle the data imbalance and this resampled data is used to fine-tune the Multilingual Bidirectional Encoder Representations from Transformers (mBERT) models. These models obtained 11th, 5th, 3rd, 3rd, and 7th ranks for English, Tamil, Malayalam, Spanish, and Hindi respectively in Task A and 8th, 2nd, and 2nd ranks for English, Tamil, and Malayalam respectively in Task B.</abstract>
<identifier type="citekey">hegde-etal-2023-mucs-lt-edi2023</identifier>
<location>
<url>https://aclanthology.org/2023.ltedi-1.44/</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>287</start>
<end>294</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MUCS@LT-EDI2023: Homophobic/Transphobic Content Detection in Social Media Text using mBERT
%A Hegde, Asha
%A G, Kavya
%A Coelho, Sharal
%A Shashirekha, Hosahalli Lakshmaiah
%Y Chakravarthi, Bharathi R.
%Y Bharathi, B.
%Y Griffith, Joephine
%Y Bali, Kalika
%Y Buitelaar, Paul
%S Proceedings of the Third Workshop on Language Technology for Equality, Diversity and Inclusion
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F hegde-etal-2023-mucs-lt-edi2023
%X Homophobic/Transphobic (H/T) content includes hate speech, discrimination text, and abusive comments against Gay, Lesbian, Bisexual, Transgender, Queer, and Intersex (LGBTQ) individuals. With the increase in user generated text in social media, there has been an increase in code-mixed H/T content, which poses challenges for efficient analysis and detection of H/T content on social media. The complex nature of code-mixed text necessitates the development of advanced tools and techniques to effectively tackle this issue in social media platforms. To tackle this issue, in this paper, we - team MUCS, describe the transformer based models submitted to “Homophobia/Transphobia Detection in social media comments” shared task in Language Technology for Equality, Diversity and Inclusion (LT-EDI) at Recent Advances in Natural Language Processing (RANLP)-2023. The proposed methodology makes use of resampling the training data to handle the data imbalance and this resampled data is used to fine-tune the Multilingual Bidirectional Encoder Representations from Transformers (mBERT) models. These models obtained 11th, 5th, 3rd, 3rd, and 7th ranks for English, Tamil, Malayalam, Spanish, and Hindi respectively in Task A and 8th, 2nd, and 2nd ranks for English, Tamil, and Malayalam respectively in Task B.
%U https://aclanthology.org/2023.ltedi-1.44/
%P 287-294
Markdown (Informal)
[MUCS@LT-EDI2023: Homophobic/Transphobic Content Detection in Social Media Text using mBERT](https://aclanthology.org/2023.ltedi-1.44/) (Hegde et al., LTEDI 2023)
ACL