@inproceedings{suman-jain-2021-astartwice,
title = "{AS}tar{T}wice at {S}em{E}val-2021 Task 5: Toxic Span Detection Using {R}o{BERT}a-{CRF}, Domain Specific Pre-Training and Self-Training",
author = "Suman, Thakur Ashutosh and
Jain, Abhinav",
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-1.118",
doi = "10.18653/v1/2021.semeval-1.118",
pages = "875--880",
abstract = "This paper describes our contribution to SemEval-2021 Task 5: Toxic Spans Detection. Our solution is built upon RoBERTa language model and Conditional Random Fields (CRF). We pre-trained RoBERTa on Civil Comments dataset, enabling it to create better contextual representation for this task. We also employed the semi-supervised learning technique of self-training, which allowed us to extend our training dataset. In addition to these, we also identified some pre-processing steps that significantly improved our F1 score. Our proposed system achieved a rank of 41 with an F1 score of 66.16{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suman-jain-2021-astartwice">
<titleInfo>
<title>AStarTwice at SemEval-2021 Task 5: Toxic Span Detection Using RoBERTa-CRF, Domain Specific Pre-Training and Self-Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thakur</namePart>
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Suman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Jain</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>This paper describes our contribution to SemEval-2021 Task 5: Toxic Spans Detection. Our solution is built upon RoBERTa language model and Conditional Random Fields (CRF). We pre-trained RoBERTa on Civil Comments dataset, enabling it to create better contextual representation for this task. We also employed the semi-supervised learning technique of self-training, which allowed us to extend our training dataset. In addition to these, we also identified some pre-processing steps that significantly improved our F1 score. Our proposed system achieved a rank of 41 with an F1 score of 66.16%.</abstract>
<identifier type="citekey">suman-jain-2021-astartwice</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.118</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.118</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>875</start>
<end>880</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AStarTwice at SemEval-2021 Task 5: Toxic Span Detection Using RoBERTa-CRF, Domain Specific Pre-Training and Self-Training
%A Suman, Thakur Ashutosh
%A Jain, Abhinav
%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 suman-jain-2021-astartwice
%X This paper describes our contribution to SemEval-2021 Task 5: Toxic Spans Detection. Our solution is built upon RoBERTa language model and Conditional Random Fields (CRF). We pre-trained RoBERTa on Civil Comments dataset, enabling it to create better contextual representation for this task. We also employed the semi-supervised learning technique of self-training, which allowed us to extend our training dataset. In addition to these, we also identified some pre-processing steps that significantly improved our F1 score. Our proposed system achieved a rank of 41 with an F1 score of 66.16%.
%R 10.18653/v1/2021.semeval-1.118
%U https://aclanthology.org/2021.semeval-1.118
%U https://doi.org/10.18653/v1/2021.semeval-1.118
%P 875-880
Markdown (Informal)
[AStarTwice at SemEval-2021 Task 5: Toxic Span Detection Using RoBERTa-CRF, Domain Specific Pre-Training and Self-Training](https://aclanthology.org/2021.semeval-1.118) (Suman & Jain, SemEval 2021)
ACL