@inproceedings{vasantharajan-thayasivam-2021-hypers,
title = "Hypers@{D}ravidian{L}ang{T}ech-{EACL}2021: Offensive language identification in {D}ravidian code-mixed {Y}ou{T}ube Comments and Posts",
author = "Vasantharajan, Charangan and
Thayasivam, Uthayasanker",
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-1.26",
pages = "195--202",
abstract = "Code-Mixed Offensive contents are used pervasively in social media posts in the last few years. Consequently, gained the significant attraction of the research community for identifying the different forms of such content (e.g., hate speech, and sentiments) and contributed to the creation of datasets. Most of the recent studies deal with high-resource languages (e.g., English) due to many publicly available datasets, and by the lack of dataset in low-resource anguages, those studies are slightly involved in these languages. Therefore, this study has the focus on offensive language identification on code-mixed low-resourced Dravidian languages such as Tamil, Kannada, and Malayalam using the bidirectional approach and fine-tuning strategies. According to the leaderboard, the proposed model got a 0.96 F1-score for Malayalam, 0.73 F1-score for Tamil, and 0.70 F1-score for Kannada in the bench-mark. Moreover, in the view of multilingual models, this modal ranked 3rd and achieved favorable results and confirmed the model as the best among all systems submitted to these shared tasks in these three languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vasantharajan-thayasivam-2021-hypers">
<titleInfo>
<title>Hypers@DravidianLangTech-EACL2021: Offensive language identification in Dravidian code-mixed YouTube Comments and Posts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Charangan</namePart>
<namePart type="family">Vasantharajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uthayasanker</namePart>
<namePart type="family">Thayasivam</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>Code-Mixed Offensive contents are used pervasively in social media posts in the last few years. Consequently, gained the significant attraction of the research community for identifying the different forms of such content (e.g., hate speech, and sentiments) and contributed to the creation of datasets. Most of the recent studies deal with high-resource languages (e.g., English) due to many publicly available datasets, and by the lack of dataset in low-resource anguages, those studies are slightly involved in these languages. Therefore, this study has the focus on offensive language identification on code-mixed low-resourced Dravidian languages such as Tamil, Kannada, and Malayalam using the bidirectional approach and fine-tuning strategies. According to the leaderboard, the proposed model got a 0.96 F1-score for Malayalam, 0.73 F1-score for Tamil, and 0.70 F1-score for Kannada in the bench-mark. Moreover, in the view of multilingual models, this modal ranked 3rd and achieved favorable results and confirmed the model as the best among all systems submitted to these shared tasks in these three languages.</abstract>
<identifier type="citekey">vasantharajan-thayasivam-2021-hypers</identifier>
<location>
<url>https://aclanthology.org/2021.dravidianlangtech-1.26</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>195</start>
<end>202</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hypers@DravidianLangTech-EACL2021: Offensive language identification in Dravidian code-mixed YouTube Comments and Posts
%A Vasantharajan, Charangan
%A Thayasivam, Uthayasanker
%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 vasantharajan-thayasivam-2021-hypers
%X Code-Mixed Offensive contents are used pervasively in social media posts in the last few years. Consequently, gained the significant attraction of the research community for identifying the different forms of such content (e.g., hate speech, and sentiments) and contributed to the creation of datasets. Most of the recent studies deal with high-resource languages (e.g., English) due to many publicly available datasets, and by the lack of dataset in low-resource anguages, those studies are slightly involved in these languages. Therefore, this study has the focus on offensive language identification on code-mixed low-resourced Dravidian languages such as Tamil, Kannada, and Malayalam using the bidirectional approach and fine-tuning strategies. According to the leaderboard, the proposed model got a 0.96 F1-score for Malayalam, 0.73 F1-score for Tamil, and 0.70 F1-score for Kannada in the bench-mark. Moreover, in the view of multilingual models, this modal ranked 3rd and achieved favorable results and confirmed the model as the best among all systems submitted to these shared tasks in these three languages.
%U https://aclanthology.org/2021.dravidianlangtech-1.26
%P 195-202
Markdown (Informal)
[Hypers@DravidianLangTech-EACL2021: Offensive language identification in Dravidian code-mixed YouTube Comments and Posts](https://aclanthology.org/2021.dravidianlangtech-1.26) (Vasantharajan & Thayasivam, DravidianLangTech 2021)
ACL