@inproceedings{tanase-etal-2020-upb,
title = "{UPB} at {S}em{E}val-2020 Task 12: Multilingual Offensive Language Detection on Social Media by Fine-tuning a Variety of {BERT}-based Models",
author = "Tanase, Mircea-Adrian and
Cercel, Dumitru-Clementin and
Chiru, Costin",
editor = "Herbelot, Aurelie and
Zhu, Xiaodan and
Palmer, Alexis and
Schneider, Nathan and
May, Jonathan and
Shutova, Ekaterina",
booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
month = dec,
year = "2020",
address = "Barcelona (online)",
publisher = "International Committee for Computational Linguistics",
url = "https://aclanthology.org/2020.semeval-1.296/",
doi = "10.18653/v1/2020.semeval-1.296",
pages = "2222--2231",
abstract = "Offensive language detection is one of the most challenging problem in the natural language processing field, being imposed by the rising presence of this phenomenon in online social media. This paper describes our Transformer-based solutions for identifying offensive language on Twitter in five languages (i.e., English, Arabic, Danish, Greek, and Turkish), which was employed in Subtask A of the Offenseval 2020 shared task. Several neural architectures (i.e., BERT, mBERT, Roberta, XLM-Roberta, and ALBERT), pre-trained using both single-language and multilingual corpora, were fine-tuned and compared using multiple combinations of datasets. Finally, the highest-scoring models were used for our submissions in the competition, which ranked our team 21st of 85, 28th of 53, 19th of 39, 16th of 37, and 10th of 46 for English, Arabic, Danish, Greek, and Turkish, respectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tanase-etal-2020-upb">
<titleInfo>
<title>UPB at SemEval-2020 Task 12: Multilingual Offensive Language Detection on Social Media by Fine-tuning a Variety of BERT-based Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mircea-Adrian</namePart>
<namePart type="family">Tanase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dumitru-Clementin</namePart>
<namePart type="family">Cercel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Costin</namePart>
<namePart type="family">Chiru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourteenth Workshop on Semantic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Offensive language detection is one of the most challenging problem in the natural language processing field, being imposed by the rising presence of this phenomenon in online social media. This paper describes our Transformer-based solutions for identifying offensive language on Twitter in five languages (i.e., English, Arabic, Danish, Greek, and Turkish), which was employed in Subtask A of the Offenseval 2020 shared task. Several neural architectures (i.e., BERT, mBERT, Roberta, XLM-Roberta, and ALBERT), pre-trained using both single-language and multilingual corpora, were fine-tuned and compared using multiple combinations of datasets. Finally, the highest-scoring models were used for our submissions in the competition, which ranked our team 21st of 85, 28th of 53, 19th of 39, 16th of 37, and 10th of 46 for English, Arabic, Danish, Greek, and Turkish, respectively.</abstract>
<identifier type="citekey">tanase-etal-2020-upb</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.296</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.296/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>2222</start>
<end>2231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UPB at SemEval-2020 Task 12: Multilingual Offensive Language Detection on Social Media by Fine-tuning a Variety of BERT-based Models
%A Tanase, Mircea-Adrian
%A Cercel, Dumitru-Clementin
%A Chiru, Costin
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y May, Jonathan
%Y Shutova, Ekaterina
%S Proceedings of the Fourteenth Workshop on Semantic Evaluation
%D 2020
%8 December
%I International Committee for Computational Linguistics
%C Barcelona (online)
%F tanase-etal-2020-upb
%X Offensive language detection is one of the most challenging problem in the natural language processing field, being imposed by the rising presence of this phenomenon in online social media. This paper describes our Transformer-based solutions for identifying offensive language on Twitter in five languages (i.e., English, Arabic, Danish, Greek, and Turkish), which was employed in Subtask A of the Offenseval 2020 shared task. Several neural architectures (i.e., BERT, mBERT, Roberta, XLM-Roberta, and ALBERT), pre-trained using both single-language and multilingual corpora, were fine-tuned and compared using multiple combinations of datasets. Finally, the highest-scoring models were used for our submissions in the competition, which ranked our team 21st of 85, 28th of 53, 19th of 39, 16th of 37, and 10th of 46 for English, Arabic, Danish, Greek, and Turkish, respectively.
%R 10.18653/v1/2020.semeval-1.296
%U https://aclanthology.org/2020.semeval-1.296/
%U https://doi.org/10.18653/v1/2020.semeval-1.296
%P 2222-2231
Markdown (Informal)
[UPB at SemEval-2020 Task 12: Multilingual Offensive Language Detection on Social Media by Fine-tuning a Variety of BERT-based Models](https://aclanthology.org/2020.semeval-1.296/) (Tanase et al., SemEval 2020)
ACL