@inproceedings{sharma-etal-2021-youngsheldon,
title = "{Y}oung{S}heldon at {S}em{E}val-2021 Task 5: Fine-tuning Pre-trained Language Models for Toxic Spans Detection using Token classification Objective",
author = "Sharma, Mayukh and
Kandasamy, Ilanthenral and
Vasantha, W.b.",
editor = "Palmer, Alexis and
Schneider, Nathan and
Schluter, Natalie and
Emerson, Guy and
Herbelot, Aurelie and
Zhu, Xiaodan",
booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.semeval-1.130",
doi = "10.18653/v1/2021.semeval-1.130",
pages = "953--959",
abstract = "In this paper, we describe our system used for SemEval 2021 Task 5: Toxic Spans Detection. Our proposed system approaches the problem as a token classification task. We trained our model to find toxic words and concatenate their spans to predict the toxic spans within a sentence. We fine-tuned Pre-trained Language Models (PLMs) for identifying the toxic words. For fine-tuning, we stacked the classification layer on top of the PLM features of each word to classify if it is toxic or not. PLMs are pre-trained using different objectives and their performance may differ on downstream tasks. We, therefore, compare the performance of BERT, ELECTRA, RoBERTa, XLM-RoBERTa, T5, XLNet, and MPNet for identifying toxic spans within a sentence. Our best performing system used RoBERTa. It performed well, achieving an F1 score of 0.6841 and secured a rank of 16 on the official leaderboard.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharma-etal-2021-youngsheldon">
<titleInfo>
<title>YoungSheldon at SemEval-2021 Task 5: Fine-tuning Pre-trained Language Models for Toxic Spans Detection using Token classification Objective</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mayukh</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilanthenral</namePart>
<namePart type="family">Kandasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">W.b.</namePart>
<namePart type="family">Vasantha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)</title>
</titleInfo>
<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">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe our system used for SemEval 2021 Task 5: Toxic Spans Detection. Our proposed system approaches the problem as a token classification task. We trained our model to find toxic words and concatenate their spans to predict the toxic spans within a sentence. We fine-tuned Pre-trained Language Models (PLMs) for identifying the toxic words. For fine-tuning, we stacked the classification layer on top of the PLM features of each word to classify if it is toxic or not. PLMs are pre-trained using different objectives and their performance may differ on downstream tasks. We, therefore, compare the performance of BERT, ELECTRA, RoBERTa, XLM-RoBERTa, T5, XLNet, and MPNet for identifying toxic spans within a sentence. Our best performing system used RoBERTa. It performed well, achieving an F1 score of 0.6841 and secured a rank of 16 on the official leaderboard.</abstract>
<identifier type="citekey">sharma-etal-2021-youngsheldon</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.130</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.130</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>953</start>
<end>959</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YoungSheldon at SemEval-2021 Task 5: Fine-tuning Pre-trained Language Models for Toxic Spans Detection using Token classification Objective
%A Sharma, Mayukh
%A Kandasamy, Ilanthenral
%A Vasantha, W.b.
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Schluter, Natalie
%Y Emerson, Guy
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%S Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F sharma-etal-2021-youngsheldon
%X In this paper, we describe our system used for SemEval 2021 Task 5: Toxic Spans Detection. Our proposed system approaches the problem as a token classification task. We trained our model to find toxic words and concatenate their spans to predict the toxic spans within a sentence. We fine-tuned Pre-trained Language Models (PLMs) for identifying the toxic words. For fine-tuning, we stacked the classification layer on top of the PLM features of each word to classify if it is toxic or not. PLMs are pre-trained using different objectives and their performance may differ on downstream tasks. We, therefore, compare the performance of BERT, ELECTRA, RoBERTa, XLM-RoBERTa, T5, XLNet, and MPNet for identifying toxic spans within a sentence. Our best performing system used RoBERTa. It performed well, achieving an F1 score of 0.6841 and secured a rank of 16 on the official leaderboard.
%R 10.18653/v1/2021.semeval-1.130
%U https://aclanthology.org/2021.semeval-1.130
%U https://doi.org/10.18653/v1/2021.semeval-1.130
%P 953-959
Markdown (Informal)
[YoungSheldon at SemEval-2021 Task 5: Fine-tuning Pre-trained Language Models for Toxic Spans Detection using Token classification Objective](https://aclanthology.org/2021.semeval-1.130) (Sharma et al., SemEval 2021)
ACL