@inproceedings{kedia-nandy-2021-indicnlp,
title = "indicnlp@kgp at {D}ravidian{L}ang{T}ech-{EACL}2021: Offensive Language Identification in {D}ravidian Languages",
author = "Kedia, Kushal and
Nandy, Abhilash",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Kumar M, Anand and
Krishnamurthy, Parameswari and
Sherly, Elizabeth",
booktitle = "Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages",
month = apr,
year = "2021",
address = "Kyiv",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.dravidianlangtech-1.48",
pages = "330--335",
abstract = "The paper aims to classify different offensive content types in 3 code-mixed Dravidian language datasets. The work leverages existing state of the art approaches in text classification by incorporating additional data and transfer learning on pre-trained models. Our final submission is an ensemble of an AWD-LSTM based model along with 2 different transformer model architectures based on BERT and RoBERTa. We achieved weighted-average F1 scores of 0.97, 0.77, and 0.72 in the Malayalam-English, Tamil-English, and Kannada-English datasets ranking 1st, 2nd, and 3rd on the respective shared-task leaderboards.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kedia-nandy-2021-indicnlp">
<titleInfo>
<title>indicnlp@kgp at DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kushal</namePart>
<namePart type="family">Kedia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhilash</namePart>
<namePart type="family">Nandy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First 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="family">Kumar M</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper aims to classify different offensive content types in 3 code-mixed Dravidian language datasets. The work leverages existing state of the art approaches in text classification by incorporating additional data and transfer learning on pre-trained models. Our final submission is an ensemble of an AWD-LSTM based model along with 2 different transformer model architectures based on BERT and RoBERTa. We achieved weighted-average F1 scores of 0.97, 0.77, and 0.72 in the Malayalam-English, Tamil-English, and Kannada-English datasets ranking 1st, 2nd, and 3rd on the respective shared-task leaderboards.</abstract>
<identifier type="citekey">kedia-nandy-2021-indicnlp</identifier>
<location>
<url>https://aclanthology.org/2021.dravidianlangtech-1.48</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>330</start>
<end>335</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T indicnlp@kgp at DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Languages
%A Kedia, Kushal
%A Nandy, Abhilash
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Kumar M, Anand
%Y Krishnamurthy, Parameswari
%Y Sherly, Elizabeth
%S Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv
%F kedia-nandy-2021-indicnlp
%X The paper aims to classify different offensive content types in 3 code-mixed Dravidian language datasets. The work leverages existing state of the art approaches in text classification by incorporating additional data and transfer learning on pre-trained models. Our final submission is an ensemble of an AWD-LSTM based model along with 2 different transformer model architectures based on BERT and RoBERTa. We achieved weighted-average F1 scores of 0.97, 0.77, and 0.72 in the Malayalam-English, Tamil-English, and Kannada-English datasets ranking 1st, 2nd, and 3rd on the respective shared-task leaderboards.
%U https://aclanthology.org/2021.dravidianlangtech-1.48
%P 330-335
Markdown (Informal)
[indicnlp@kgp at DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Languages](https://aclanthology.org/2021.dravidianlangtech-1.48) (Kedia & Nandy, DravidianLangTech 2021)
ACL