@inproceedings{wu-etal-2019-bnu,
title = "{BNU}-{HKBU} {UIC} {NLP} Team 2 at {S}em{E}val-2019 Task 6: Detecting Offensive Language Using {BERT} model",
author = "Wu, Zhenghao and
Zheng, Hao and
Wang, Jianming and
Su, Weifeng and
Fong, Jefferson",
editor = "May, Jonathan and
Shutova, Ekaterina and
Herbelot, Aurelie and
Zhu, Xiaodan and
Apidianaki, Marianna and
Mohammad, Saif M.",
booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S19-2099",
doi = "10.18653/v1/S19-2099",
pages = "551--555",
abstract = "In this study we deal with the problem of identifying and categorizing offensive language in social media. Our group, BNU-HKBU UIC NLP Team2, use supervised classification along with multiple version of data generated by different ways of pre-processing the data. We then use the state-of-the-art model Bidirectional Encoder Representations from Transformers, or BERT (Devlin et al, 2018), to capture linguistic, syntactic and semantic features. Long range dependencies between each part of a sentence can be captured by BERT{'}s bidirectional encoder representations. Our results show 85.12{\%} accuracy and 80.57{\%} F1 scores in Subtask A (offensive language identification), 87.92{\%} accuracy and 50{\%} F1 scores in Subtask B (categorization of offense types), and 69.95{\%} accuracy and 50.47{\%} F1 score in Subtask C (offense target identification). Analysis of the results shows that distinguishing between targeted and untargeted offensive language is not a simple task. More work needs to be done on the unbalance data problem in Subtasks B and C. Some future work is also discussed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2019-bnu">
<titleInfo>
<title>BNU-HKBU UIC NLP Team 2 at SemEval-2019 Task 6: Detecting Offensive Language Using BERT model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhenghao</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianming</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weifeng</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jefferson</namePart>
<namePart type="family">Fong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Workshop on Semantic Evaluation</title>
</titleInfo>
<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>
<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">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this study we deal with the problem of identifying and categorizing offensive language in social media. Our group, BNU-HKBU UIC NLP Team2, use supervised classification along with multiple version of data generated by different ways of pre-processing the data. We then use the state-of-the-art model Bidirectional Encoder Representations from Transformers, or BERT (Devlin et al, 2018), to capture linguistic, syntactic and semantic features. Long range dependencies between each part of a sentence can be captured by BERT’s bidirectional encoder representations. Our results show 85.12% accuracy and 80.57% F1 scores in Subtask A (offensive language identification), 87.92% accuracy and 50% F1 scores in Subtask B (categorization of offense types), and 69.95% accuracy and 50.47% F1 score in Subtask C (offense target identification). Analysis of the results shows that distinguishing between targeted and untargeted offensive language is not a simple task. More work needs to be done on the unbalance data problem in Subtasks B and C. Some future work is also discussed.</abstract>
<identifier type="citekey">wu-etal-2019-bnu</identifier>
<identifier type="doi">10.18653/v1/S19-2099</identifier>
<location>
<url>https://aclanthology.org/S19-2099</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>551</start>
<end>555</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BNU-HKBU UIC NLP Team 2 at SemEval-2019 Task 6: Detecting Offensive Language Using BERT model
%A Wu, Zhenghao
%A Zheng, Hao
%A Wang, Jianming
%A Su, Weifeng
%A Fong, Jefferson
%Y May, Jonathan
%Y Shutova, Ekaterina
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Apidianaki, Marianna
%Y Mohammad, Saif M.
%S Proceedings of the 13th International Workshop on Semantic Evaluation
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota, USA
%F wu-etal-2019-bnu
%X In this study we deal with the problem of identifying and categorizing offensive language in social media. Our group, BNU-HKBU UIC NLP Team2, use supervised classification along with multiple version of data generated by different ways of pre-processing the data. We then use the state-of-the-art model Bidirectional Encoder Representations from Transformers, or BERT (Devlin et al, 2018), to capture linguistic, syntactic and semantic features. Long range dependencies between each part of a sentence can be captured by BERT’s bidirectional encoder representations. Our results show 85.12% accuracy and 80.57% F1 scores in Subtask A (offensive language identification), 87.92% accuracy and 50% F1 scores in Subtask B (categorization of offense types), and 69.95% accuracy and 50.47% F1 score in Subtask C (offense target identification). Analysis of the results shows that distinguishing between targeted and untargeted offensive language is not a simple task. More work needs to be done on the unbalance data problem in Subtasks B and C. Some future work is also discussed.
%R 10.18653/v1/S19-2099
%U https://aclanthology.org/S19-2099
%U https://doi.org/10.18653/v1/S19-2099
%P 551-555
Markdown (Informal)
[BNU-HKBU UIC NLP Team 2 at SemEval-2019 Task 6: Detecting Offensive Language Using BERT model](https://aclanthology.org/S19-2099) (Wu et al., SemEval 2019)
ACL