@inproceedings{li-2021-codewithzichao,
title = "Codewithzichao@{D}ravidian{L}ang{T}ech-{EACL}2021: Exploring Multilingual Transformers for Offensive Language Identification on Code Mixing Text",
author = "Li, Zichao",
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-1.21/",
pages = "164--168",
abstract = "This paper describes our solution submitted to shared task on Offensive Language Identification in Dravidian Languages. We participated in all three of offensive language identification. In order to address the task, we explored multilingual models based on XLM-RoBERTa and multilingual BERT trained on mixed data of three code-mixed languages. Besides, we solved the class-imbalance problem existed in training data by class combination, class weights and focal loss. Our model achieved weighted average F1 scores of 0.75 (ranked 4th), 0.94 (ranked 4th) and 0.72 (ranked 3rd) in Tamil-English task, Malayalam-English task and Kannada-English task, respectively."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-2021-codewithzichao">
<titleInfo>
<title>Codewithzichao@DravidianLangTech-EACL2021: Exploring Multilingual Transformers for Offensive Language Identification on Code Mixing Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zichao</namePart>
<namePart type="family">Li</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>This paper describes our solution submitted to shared task on Offensive Language Identification in Dravidian Languages. We participated in all three of offensive language identification. In order to address the task, we explored multilingual models based on XLM-RoBERTa and multilingual BERT trained on mixed data of three code-mixed languages. Besides, we solved the class-imbalance problem existed in training data by class combination, class weights and focal loss. Our model achieved weighted average F1 scores of 0.75 (ranked 4th), 0.94 (ranked 4th) and 0.72 (ranked 3rd) in Tamil-English task, Malayalam-English task and Kannada-English task, respectively.</abstract>
<identifier type="citekey">li-2021-codewithzichao</identifier>
<location>
<url>https://aclanthology.org/2021.dravidianlangtech-1.21/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>164</start>
<end>168</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Codewithzichao@DravidianLangTech-EACL2021: Exploring Multilingual Transformers for Offensive Language Identification on Code Mixing Text
%A Li, Zichao
%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 li-2021-codewithzichao
%X This paper describes our solution submitted to shared task on Offensive Language Identification in Dravidian Languages. We participated in all three of offensive language identification. In order to address the task, we explored multilingual models based on XLM-RoBERTa and multilingual BERT trained on mixed data of three code-mixed languages. Besides, we solved the class-imbalance problem existed in training data by class combination, class weights and focal loss. Our model achieved weighted average F1 scores of 0.75 (ranked 4th), 0.94 (ranked 4th) and 0.72 (ranked 3rd) in Tamil-English task, Malayalam-English task and Kannada-English task, respectively.
%U https://aclanthology.org/2021.dravidianlangtech-1.21/
%P 164-168
Markdown (Informal)
[Codewithzichao@DravidianLangTech-EACL2021: Exploring Multilingual Transformers for Offensive Language Identification on Code Mixing Text](https://aclanthology.org/2021.dravidianlangtech-1.21/) (Li, DravidianLangTech 2021)
ACL