@inproceedings{dale-etal-2021-skoltechnlp,
title = "{S}koltech{NLP} at {S}em{E}val-2021 Task 5: Leveraging Sentence-level Pre-training for Toxic Span Detection",
author = "Dale, David and
Markov, Igor and
Logacheva, Varvara and
Kozlova, Olga and
Semenov, Nikita and
Panchenko, Alexander",
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-1.126",
doi = "10.18653/v1/2021.semeval-1.126",
pages = "927--934",
abstract = "This work describes the participation of the Skoltech NLP group team (Sk) in the Toxic Spans Detection task at SemEval-2021. The goal of the task is to identify the most toxic fragments of a given sentence, which is a binary sequence tagging problem. We show that fine-tuning a RoBERTa model for this problem is a strong baseline. This baseline can be further improved by pre-training the RoBERTa model on a large dataset labeled for toxicity at the sentence level. While our solution scored among the top 20{\%} participating models, it is only 2 points below the best result. This suggests the viability of our approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dale-etal-2021-skoltechnlp">
<titleInfo>
<title>SkoltechNLP at SemEval-2021 Task 5: Leveraging Sentence-level Pre-training for Toxic Span Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Dale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Igor</namePart>
<namePart type="family">Markov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Kozlova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikita</namePart>
<namePart type="family">Semenov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Panchenko</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 work describes the participation of the Skoltech NLP group team (Sk) in the Toxic Spans Detection task at SemEval-2021. The goal of the task is to identify the most toxic fragments of a given sentence, which is a binary sequence tagging problem. We show that fine-tuning a RoBERTa model for this problem is a strong baseline. This baseline can be further improved by pre-training the RoBERTa model on a large dataset labeled for toxicity at the sentence level. While our solution scored among the top 20% participating models, it is only 2 points below the best result. This suggests the viability of our approach.</abstract>
<identifier type="citekey">dale-etal-2021-skoltechnlp</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.126</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.126</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>927</start>
<end>934</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SkoltechNLP at SemEval-2021 Task 5: Leveraging Sentence-level Pre-training for Toxic Span Detection
%A Dale, David
%A Markov, Igor
%A Logacheva, Varvara
%A Kozlova, Olga
%A Semenov, Nikita
%A Panchenko, Alexander
%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 dale-etal-2021-skoltechnlp
%X This work describes the participation of the Skoltech NLP group team (Sk) in the Toxic Spans Detection task at SemEval-2021. The goal of the task is to identify the most toxic fragments of a given sentence, which is a binary sequence tagging problem. We show that fine-tuning a RoBERTa model for this problem is a strong baseline. This baseline can be further improved by pre-training the RoBERTa model on a large dataset labeled for toxicity at the sentence level. While our solution scored among the top 20% participating models, it is only 2 points below the best result. This suggests the viability of our approach.
%R 10.18653/v1/2021.semeval-1.126
%U https://aclanthology.org/2021.semeval-1.126
%U https://doi.org/10.18653/v1/2021.semeval-1.126
%P 927-934
Markdown (Informal)
[SkoltechNLP at SemEval-2021 Task 5: Leveraging Sentence-level Pre-training for Toxic Span Detection](https://aclanthology.org/2021.semeval-1.126) (Dale et al., SemEval 2021)
ACL