@inproceedings{chen-etal-2020-ferryman-semeval-2020-task,
title = "Ferryman at {S}em{E}val-2020 Task 12: {BERT}-Based Model with Advanced Improvement Methods for Multilingual Offensive Language Identification",
author = "Chen, Weilong and
Wang, Peng and
Li, Jipeng and
Zheng, Yuanshuai and
Wang, Yan and
Zhang, Yanru",
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-1.256",
doi = "10.18653/v1/2020.semeval-1.256",
pages = "1947--1952",
abstract = "Indiscriminately posting offensive remarks on social media may promote the occurrence of negative events such as violence, crime, and hatred. This paper examines different approaches and models for solving offensive tweet classification, which is a part of the OffensEval 2020 competition. The dataset is Offensive Language Identification Dataset (OLID), which draws 14,200 annotated English Tweet comments. The main challenge of data preprocessing is the unbalanced class distribution, abbreviation, and emoji. To overcome these issues, methods such as hashtag segmentation, abbreviation replacement, and emoji replacement have been adopted for data preprocessing approaches. The main task can be divided into three sub-tasks, and are solved by Term Frequency{--}Inverse Document Frequency(TF-IDF), Bidirectional Encoder Representation from Transformer (BERT), and Multi-dropout respectively. Meanwhile, we applied different learning rates for different languages and tasks based on BERT and non-BERTmodels in order to obtain better results. Our team Ferryman ranked the 18th, 8th, and 21st with F1-score of 0.91152 on the English Sub-task A, Sub-task B, and Sub-task C, respectively. Furthermore, our team also ranked in the top 20 on the Sub-task A of other languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2020-ferryman-semeval-2020-task">
<titleInfo>
<title>Ferryman at SemEval-2020 Task 12: BERT-Based Model with Advanced Improvement Methods for Multilingual Offensive Language Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weilong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jipeng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanshuai</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanru</namePart>
<namePart type="family">Zhang</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>Indiscriminately posting offensive remarks on social media may promote the occurrence of negative events such as violence, crime, and hatred. This paper examines different approaches and models for solving offensive tweet classification, which is a part of the OffensEval 2020 competition. The dataset is Offensive Language Identification Dataset (OLID), which draws 14,200 annotated English Tweet comments. The main challenge of data preprocessing is the unbalanced class distribution, abbreviation, and emoji. To overcome these issues, methods such as hashtag segmentation, abbreviation replacement, and emoji replacement have been adopted for data preprocessing approaches. The main task can be divided into three sub-tasks, and are solved by Term Frequency–Inverse Document Frequency(TF-IDF), Bidirectional Encoder Representation from Transformer (BERT), and Multi-dropout respectively. Meanwhile, we applied different learning rates for different languages and tasks based on BERT and non-BERTmodels in order to obtain better results. Our team Ferryman ranked the 18th, 8th, and 21st with F1-score of 0.91152 on the English Sub-task A, Sub-task B, and Sub-task C, respectively. Furthermore, our team also ranked in the top 20 on the Sub-task A of other languages.</abstract>
<identifier type="citekey">chen-etal-2020-ferryman-semeval-2020-task</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.256</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.256</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1947</start>
<end>1952</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ferryman at SemEval-2020 Task 12: BERT-Based Model with Advanced Improvement Methods for Multilingual Offensive Language Identification
%A Chen, Weilong
%A Wang, Peng
%A Li, Jipeng
%A Zheng, Yuanshuai
%A Wang, Yan
%A Zhang, Yanru
%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 chen-etal-2020-ferryman-semeval-2020-task
%X Indiscriminately posting offensive remarks on social media may promote the occurrence of negative events such as violence, crime, and hatred. This paper examines different approaches and models for solving offensive tweet classification, which is a part of the OffensEval 2020 competition. The dataset is Offensive Language Identification Dataset (OLID), which draws 14,200 annotated English Tweet comments. The main challenge of data preprocessing is the unbalanced class distribution, abbreviation, and emoji. To overcome these issues, methods such as hashtag segmentation, abbreviation replacement, and emoji replacement have been adopted for data preprocessing approaches. The main task can be divided into three sub-tasks, and are solved by Term Frequency–Inverse Document Frequency(TF-IDF), Bidirectional Encoder Representation from Transformer (BERT), and Multi-dropout respectively. Meanwhile, we applied different learning rates for different languages and tasks based on BERT and non-BERTmodels in order to obtain better results. Our team Ferryman ranked the 18th, 8th, and 21st with F1-score of 0.91152 on the English Sub-task A, Sub-task B, and Sub-task C, respectively. Furthermore, our team also ranked in the top 20 on the Sub-task A of other languages.
%R 10.18653/v1/2020.semeval-1.256
%U https://aclanthology.org/2020.semeval-1.256
%U https://doi.org/10.18653/v1/2020.semeval-1.256
%P 1947-1952
Markdown (Informal)
[Ferryman at SemEval-2020 Task 12: BERT-Based Model with Advanced Improvement Methods for Multilingual Offensive Language Identification](https://aclanthology.org/2020.semeval-1.256) (Chen et al., SemEval 2020)
ACL