@inproceedings{swaminathan-etal-2022-pandas,
title = "{PANDAS}@Abusive Comment Detection in {T}amil Code-Mixed Data Using Custom Embeddings with {L}a{BSE}",
author = "G L, Gayathri and
Swaminathan, Krithika and
K, Divyasri and
Durairaj, Thenmozhi and
B, Bharathi",
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-1.18",
doi = "10.18653/v1/2022.dravidianlangtech-1.18",
pages = "112--119",
abstract = "Abusive language has lately been prevalent in comments on various social media platforms. The increasing hostility observed on the internet calls for the creation of a system that can identify and flag such acerbic content, to prevent conflict and mental distress. This task becomes more challenging when low-resource languages like Tamil, as well as the often-observed Tamil-English code-mixed text, are involved. The approach used in this paper for the classification model includes different methods of feature extraction and the use of traditional classifiers. We propose a novel method of combining language-agnostic sentence embeddings with the TF-IDF vector representation that uses a curated corpus of words as vocabulary, to create a custom embedding, which is then passed to an SVM classifier. Our experimentation yielded an accuracy of 52{\%} and an F1-score of 0.54.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="swaminathan-etal-2022-pandas">
<titleInfo>
<title>PANDAS@Abusive Comment Detection in Tamil Code-Mixed Data Using Custom Embeddings with LaBSE</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gayathri</namePart>
<namePart type="family">G L</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krithika</namePart>
<namePart type="family">Swaminathan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Divyasri</namePart>
<namePart type="family">K</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thenmozhi</namePart>
<namePart type="family">Durairaj</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>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>Abusive language has lately been prevalent in comments on various social media platforms. The increasing hostility observed on the internet calls for the creation of a system that can identify and flag such acerbic content, to prevent conflict and mental distress. This task becomes more challenging when low-resource languages like Tamil, as well as the often-observed Tamil-English code-mixed text, are involved. The approach used in this paper for the classification model includes different methods of feature extraction and the use of traditional classifiers. We propose a novel method of combining language-agnostic sentence embeddings with the TF-IDF vector representation that uses a curated corpus of words as vocabulary, to create a custom embedding, which is then passed to an SVM classifier. Our experimentation yielded an accuracy of 52% and an F1-score of 0.54.</abstract>
<identifier type="citekey">swaminathan-etal-2022-pandas</identifier>
<identifier type="doi">10.18653/v1/2022.dravidianlangtech-1.18</identifier>
<location>
<url>https://aclanthology.org/2022.dravidianlangtech-1.18</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>112</start>
<end>119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PANDAS@Abusive Comment Detection in Tamil Code-Mixed Data Using Custom Embeddings with LaBSE
%A G L, Gayathri
%A Swaminathan, Krithika
%A K, Divyasri
%A Durairaj, Thenmozhi
%A B, Bharathi
%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 swaminathan-etal-2022-pandas
%X Abusive language has lately been prevalent in comments on various social media platforms. The increasing hostility observed on the internet calls for the creation of a system that can identify and flag such acerbic content, to prevent conflict and mental distress. This task becomes more challenging when low-resource languages like Tamil, as well as the often-observed Tamil-English code-mixed text, are involved. The approach used in this paper for the classification model includes different methods of feature extraction and the use of traditional classifiers. We propose a novel method of combining language-agnostic sentence embeddings with the TF-IDF vector representation that uses a curated corpus of words as vocabulary, to create a custom embedding, which is then passed to an SVM classifier. Our experimentation yielded an accuracy of 52% and an F1-score of 0.54.
%R 10.18653/v1/2022.dravidianlangtech-1.18
%U https://aclanthology.org/2022.dravidianlangtech-1.18
%U https://doi.org/10.18653/v1/2022.dravidianlangtech-1.18
%P 112-119
Markdown (Informal)
[PANDAS@Abusive Comment Detection in Tamil Code-Mixed Data Using Custom Embeddings with LaBSE](https://aclanthology.org/2022.dravidianlangtech-1.18) (G L et al., DravidianLangTech 2022)
ACL