@inproceedings{yao-etal-2020-ujnlp,
title = "{UJNLP} at {S}em{E}val-2020 Task 12: Detecting Offensive Language Using Bidirectional Transformers",
author = "Yao, Yinnan and
Su, Nan and
Ma, Kun",
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-1.293/",
doi = "10.18653/v1/2020.semeval-1.293",
pages = "2203--2208",
abstract = "In this paper, we built several pre-trained models to participate SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media. In the common task of Offensive Language Identification in Social Media, pre-trained models such as Bidirectional Encoder Representation from Transformer (BERT) have achieved good results. We preprocess the dataset by the language habits of users in social network. Considering the data imbalance in OffensEval, we screened the newly provided machine annotation samples to construct a new dataset. We use the dataset to fine-tune the Robustly Optimized BERT Pretraining Approach (RoBERTa). For the English subtask B, we adopted the method of adding Auxiliary Sentences (AS) to transform the single-sentence classification task into a relationship recognition task between sentences. Our team UJNLP wins the ranking 16th of 85 in English subtask A (Offensive language identification)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yao-etal-2020-ujnlp">
<titleInfo>
<title>UJNLP at SemEval-2020 Task 12: Detecting Offensive Language Using Bidirectional Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yinnan</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Ma</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>In this paper, we built several pre-trained models to participate SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media. In the common task of Offensive Language Identification in Social Media, pre-trained models such as Bidirectional Encoder Representation from Transformer (BERT) have achieved good results. We preprocess the dataset by the language habits of users in social network. Considering the data imbalance in OffensEval, we screened the newly provided machine annotation samples to construct a new dataset. We use the dataset to fine-tune the Robustly Optimized BERT Pretraining Approach (RoBERTa). For the English subtask B, we adopted the method of adding Auxiliary Sentences (AS) to transform the single-sentence classification task into a relationship recognition task between sentences. Our team UJNLP wins the ranking 16th of 85 in English subtask A (Offensive language identification).</abstract>
<identifier type="citekey">yao-etal-2020-ujnlp</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.293</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.293/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>2203</start>
<end>2208</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UJNLP at SemEval-2020 Task 12: Detecting Offensive Language Using Bidirectional Transformers
%A Yao, Yinnan
%A Su, Nan
%A Ma, Kun
%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 yao-etal-2020-ujnlp
%X In this paper, we built several pre-trained models to participate SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media. In the common task of Offensive Language Identification in Social Media, pre-trained models such as Bidirectional Encoder Representation from Transformer (BERT) have achieved good results. We preprocess the dataset by the language habits of users in social network. Considering the data imbalance in OffensEval, we screened the newly provided machine annotation samples to construct a new dataset. We use the dataset to fine-tune the Robustly Optimized BERT Pretraining Approach (RoBERTa). For the English subtask B, we adopted the method of adding Auxiliary Sentences (AS) to transform the single-sentence classification task into a relationship recognition task between sentences. Our team UJNLP wins the ranking 16th of 85 in English subtask A (Offensive language identification).
%R 10.18653/v1/2020.semeval-1.293
%U https://aclanthology.org/2020.semeval-1.293/
%U https://doi.org/10.18653/v1/2020.semeval-1.293
%P 2203-2208
Markdown (Informal)
[UJNLP at SemEval-2020 Task 12: Detecting Offensive Language Using Bidirectional Transformers](https://aclanthology.org/2020.semeval-1.293/) (Yao et al., SemEval 2020)
ACL