@inproceedings{prasad-etal-2022-gjg-tamilnlp,
title = "{GJG}@{T}amil{NLP}-{ACL}2022: Using Transformers for Abusive Comment Classification in {T}amil",
author = "Prasad, Gaurang and
Prasad, Janvi and
C, Gunavathi",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Krishnamurthy, Parameswari and
Sherly, Elizabeth and
Mahesan, Sinnathamby",
booktitle = "Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.dravidianlangtech-1.15/",
doi = "10.18653/v1/2022.dravidianlangtech-1.15",
pages = "93--99",
abstract = "This paper presents transformer-based models for the {\textquotedblleft}Abusive Comment Detection{\textquotedblright} shared task at the Second Workshop on Speech and Language Technologies for Dravidian Languages at ACL 2022. Our team participated in both the multi-class classification sub-tasks as a part of this shared task. The dataset for sub-task A was in Tamil text; while B was code-mixed Tamil-English text. Both the datasets contained 8 classes of abusive comments. We trained an XLM-RoBERTa and DeBERTA base model on the training splits for each sub-task. For sub-task A, the XLM-RoBERTa model achieved an accuracy of 0.66 and the DeBERTa model achieved an accuracy of 0.62. For sub-task B, both the models achieved a classification accuracy of 0.72; however, the DeBERTa model performed better in other classification metrics. Our team ranked 2nd in the code-mixed classification sub-task and 8th in Tamil-text sub-task."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="prasad-etal-2022-gjg-tamilnlp">
<titleInfo>
<title>GJG@TamilNLP-ACL2022: Using Transformers for Abusive Comment Classification in Tamil</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gaurang</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janvi</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gunavathi</namePart>
<namePart type="family">C</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Speech 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">Parameswari</namePart>
<namePart type="family">Krishnamurthy</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">Sinnathamby</namePart>
<namePart type="family">Mahesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents transformer-based models for the “Abusive Comment Detection” shared task at the Second Workshop on Speech and Language Technologies for Dravidian Languages at ACL 2022. Our team participated in both the multi-class classification sub-tasks as a part of this shared task. The dataset for sub-task A was in Tamil text; while B was code-mixed Tamil-English text. Both the datasets contained 8 classes of abusive comments. We trained an XLM-RoBERTa and DeBERTA base model on the training splits for each sub-task. For sub-task A, the XLM-RoBERTa model achieved an accuracy of 0.66 and the DeBERTa model achieved an accuracy of 0.62. For sub-task B, both the models achieved a classification accuracy of 0.72; however, the DeBERTa model performed better in other classification metrics. Our team ranked 2nd in the code-mixed classification sub-task and 8th in Tamil-text sub-task.</abstract>
<identifier type="citekey">prasad-etal-2022-gjg-tamilnlp</identifier>
<identifier type="doi">10.18653/v1/2022.dravidianlangtech-1.15</identifier>
<location>
<url>https://aclanthology.org/2022.dravidianlangtech-1.15/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>93</start>
<end>99</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GJG@TamilNLP-ACL2022: Using Transformers for Abusive Comment Classification in Tamil
%A Prasad, Gaurang
%A Prasad, Janvi
%A C, Gunavathi
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Krishnamurthy, Parameswari
%Y Sherly, Elizabeth
%Y Mahesan, Sinnathamby
%S Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F prasad-etal-2022-gjg-tamilnlp
%X This paper presents transformer-based models for the “Abusive Comment Detection” shared task at the Second Workshop on Speech and Language Technologies for Dravidian Languages at ACL 2022. Our team participated in both the multi-class classification sub-tasks as a part of this shared task. The dataset for sub-task A was in Tamil text; while B was code-mixed Tamil-English text. Both the datasets contained 8 classes of abusive comments. We trained an XLM-RoBERTa and DeBERTA base model on the training splits for each sub-task. For sub-task A, the XLM-RoBERTa model achieved an accuracy of 0.66 and the DeBERTa model achieved an accuracy of 0.62. For sub-task B, both the models achieved a classification accuracy of 0.72; however, the DeBERTa model performed better in other classification metrics. Our team ranked 2nd in the code-mixed classification sub-task and 8th in Tamil-text sub-task.
%R 10.18653/v1/2022.dravidianlangtech-1.15
%U https://aclanthology.org/2022.dravidianlangtech-1.15/
%U https://doi.org/10.18653/v1/2022.dravidianlangtech-1.15
%P 93-99
Markdown (Informal)
[GJG@TamilNLP-ACL2022: Using Transformers for Abusive Comment Classification in Tamil](https://aclanthology.org/2022.dravidianlangtech-1.15/) (Prasad et al., DravidianLangTech 2022)
ACL