@inproceedings{wang-etal-2020-galileo,
title = "Galileo at {S}em{E}val-2020 Task 12: Multi-lingual Learning for Offensive Language Identification Using Pre-trained Language Models",
author = "Wang, Shuohuan and
Liu, Jiaxiang and
Ouyang, Xuan and
Sun, Yu",
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-1.189",
doi = "10.18653/v1/2020.semeval-1.189",
pages = "1448--1455",
abstract = "This paper describes Galileo{'}s performance in SemEval-2020 Task 12 on detecting and categorizing offensive language in social media. For Offensive Language Identification, we proposed a multi-lingual method using Pre-trained Language Models, ERNIE and XLM-R. For offensive language categorization, we proposed a knowledge distillation method trained on soft labels generated by several supervised models. Our team participated in all three sub-tasks. In Sub-task A - Offensive Language Identification, we ranked first in terms of average F1 scores in all languages. We are also the only team which ranked among the top three across all languages. We also took the first place in Sub-task B - Automatic Categorization of Offense Types and Sub-task C - Offence Target Identification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2020-galileo">
<titleInfo>
<title>Galileo at SemEval-2020 Task 12: Multi-lingual Learning for Offensive Language Identification Using Pre-trained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuohuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxiang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Sun</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>This paper describes Galileo’s performance in SemEval-2020 Task 12 on detecting and categorizing offensive language in social media. For Offensive Language Identification, we proposed a multi-lingual method using Pre-trained Language Models, ERNIE and XLM-R. For offensive language categorization, we proposed a knowledge distillation method trained on soft labels generated by several supervised models. Our team participated in all three sub-tasks. In Sub-task A - Offensive Language Identification, we ranked first in terms of average F1 scores in all languages. We are also the only team which ranked among the top three across all languages. We also took the first place in Sub-task B - Automatic Categorization of Offense Types and Sub-task C - Offence Target Identification.</abstract>
<identifier type="citekey">wang-etal-2020-galileo</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.189</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.189</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1448</start>
<end>1455</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Galileo at SemEval-2020 Task 12: Multi-lingual Learning for Offensive Language Identification Using Pre-trained Language Models
%A Wang, Shuohuan
%A Liu, Jiaxiang
%A Ouyang, Xuan
%A Sun, Yu
%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 wang-etal-2020-galileo
%X This paper describes Galileo’s performance in SemEval-2020 Task 12 on detecting and categorizing offensive language in social media. For Offensive Language Identification, we proposed a multi-lingual method using Pre-trained Language Models, ERNIE and XLM-R. For offensive language categorization, we proposed a knowledge distillation method trained on soft labels generated by several supervised models. Our team participated in all three sub-tasks. In Sub-task A - Offensive Language Identification, we ranked first in terms of average F1 scores in all languages. We are also the only team which ranked among the top three across all languages. We also took the first place in Sub-task B - Automatic Categorization of Offense Types and Sub-task C - Offence Target Identification.
%R 10.18653/v1/2020.semeval-1.189
%U https://aclanthology.org/2020.semeval-1.189
%U https://doi.org/10.18653/v1/2020.semeval-1.189
%P 1448-1455
Markdown (Informal)
[Galileo at SemEval-2020 Task 12: Multi-lingual Learning for Offensive Language Identification Using Pre-trained Language Models](https://aclanthology.org/2020.semeval-1.189) (Wang et al., SemEval 2020)
ACL