@inproceedings{garain-etal-2021-junlp,
title = "{JUNLP}@{D}ravidian{L}ang{T}ech-{EACL}2021: Offensive Language Identification in {D}ravidian Langauges",
author = "Garain, Avishek and
Mandal, Atanu and
Naskar, Sudip Kumar",
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-1.46",
pages = "319--322",
abstract = "Offensive language identification has been an active area of research in natural language processing. With the emergence of multiple social media platforms offensive language identification has emerged as a need of the hour. Traditional offensive language identification models fail to deliver acceptable results as social media contents are largely in multilingual and are code-mixed in nature. This paper tries to resolve this problem by using IndicBERT and BERT architectures, to facilitate identification of offensive languages for Kannada-English, Malayalam-English, and Tamil-English code-mixed language pairs extracted from social media. The presented approach when evaluated on the test corpus provided precision, recall, and F1 score for language pair Kannada-English as 0.62, 0.71, and 0.66, respectively, for language pair Malayalam-English as 0.77, 0.43, and 0.53, respectively, and for Tamil-English as 0.71, 0.74, and 0.72, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garain-etal-2021-junlp">
<titleInfo>
<title>JUNLP@DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Langauges</title>
</titleInfo>
<name type="personal">
<namePart type="given">Avishek</namePart>
<namePart type="family">Garain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atanu</namePart>
<namePart type="family">Mandal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudip</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Naskar</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>Offensive language identification has been an active area of research in natural language processing. With the emergence of multiple social media platforms offensive language identification has emerged as a need of the hour. Traditional offensive language identification models fail to deliver acceptable results as social media contents are largely in multilingual and are code-mixed in nature. This paper tries to resolve this problem by using IndicBERT and BERT architectures, to facilitate identification of offensive languages for Kannada-English, Malayalam-English, and Tamil-English code-mixed language pairs extracted from social media. The presented approach when evaluated on the test corpus provided precision, recall, and F1 score for language pair Kannada-English as 0.62, 0.71, and 0.66, respectively, for language pair Malayalam-English as 0.77, 0.43, and 0.53, respectively, and for Tamil-English as 0.71, 0.74, and 0.72, respectively.</abstract>
<identifier type="citekey">garain-etal-2021-junlp</identifier>
<location>
<url>https://aclanthology.org/2021.dravidianlangtech-1.46</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>319</start>
<end>322</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JUNLP@DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Langauges
%A Garain, Avishek
%A Mandal, Atanu
%A Naskar, Sudip Kumar
%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 garain-etal-2021-junlp
%X Offensive language identification has been an active area of research in natural language processing. With the emergence of multiple social media platforms offensive language identification has emerged as a need of the hour. Traditional offensive language identification models fail to deliver acceptable results as social media contents are largely in multilingual and are code-mixed in nature. This paper tries to resolve this problem by using IndicBERT and BERT architectures, to facilitate identification of offensive languages for Kannada-English, Malayalam-English, and Tamil-English code-mixed language pairs extracted from social media. The presented approach when evaluated on the test corpus provided precision, recall, and F1 score for language pair Kannada-English as 0.62, 0.71, and 0.66, respectively, for language pair Malayalam-English as 0.77, 0.43, and 0.53, respectively, and for Tamil-English as 0.71, 0.74, and 0.72, respectively.
%U https://aclanthology.org/2021.dravidianlangtech-1.46
%P 319-322
Markdown (Informal)
[JUNLP@DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Langauges](https://aclanthology.org/2021.dravidianlangtech-1.46) (Garain et al., DravidianLangTech 2021)
ACL