@inproceedings{satlawa-etal-2021-srpol,
title = "{SRPOL} {DIALOGUE} {SYSTEMS} at {S}em{E}val-2021 Task 5: Automatic Generation of Training Data for Toxic Spans Detection",
author = "Sat{\l}awa, Micha{\l} and
Zam{\l}y{\'n}ska, Katarzyna and
Piersa, Jaros{\l}aw and
Kolis, Joanna and
Firl{\k{a}}g, Klaudia and
Beksa, Katarzyna and
Bordzicka, Zuzanna and
Goltz, Christian and
Bujnowski, Pawe{\l} and
Andruszkiewicz, Piotr",
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-1.133",
doi = "10.18653/v1/2021.semeval-1.133",
pages = "974--983",
abstract = "This paper presents a system used for SemEval-2021 Task 5: Toxic Spans Detection. Our system is an ensemble of BERT-based models for binary word classification, trained on a dataset extended by toxic comments modified and generated by two language models. For the toxic word classification, the prediction threshold value was optimized separately for every comment, in order to maximize the expected F1 value.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="satlawa-etal-2021-srpol">
<titleInfo>
<title>SRPOL DIALOGUE SYSTEMS at SemEval-2021 Task 5: Automatic Generation of Training Data for Toxic Spans Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Satława</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katarzyna</namePart>
<namePart type="family">Zamłyńska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jarosław</namePart>
<namePart type="family">Piersa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Kolis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Klaudia</namePart>
<namePart type="family">Firląg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katarzyna</namePart>
<namePart type="family">Beksa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zuzanna</namePart>
<namePart type="family">Bordzicka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Goltz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paweł</namePart>
<namePart type="family">Bujnowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Andruszkiewicz</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 presents a system used for SemEval-2021 Task 5: Toxic Spans Detection. Our system is an ensemble of BERT-based models for binary word classification, trained on a dataset extended by toxic comments modified and generated by two language models. For the toxic word classification, the prediction threshold value was optimized separately for every comment, in order to maximize the expected F1 value.</abstract>
<identifier type="citekey">satlawa-etal-2021-srpol</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.133</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.133</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>974</start>
<end>983</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SRPOL DIALOGUE SYSTEMS at SemEval-2021 Task 5: Automatic Generation of Training Data for Toxic Spans Detection
%A Satława, Michał
%A Zamłyńska, Katarzyna
%A Piersa, Jarosław
%A Kolis, Joanna
%A Firląg, Klaudia
%A Beksa, Katarzyna
%A Bordzicka, Zuzanna
%A Goltz, Christian
%A Bujnowski, Paweł
%A Andruszkiewicz, Piotr
%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 satlawa-etal-2021-srpol
%X This paper presents a system used for SemEval-2021 Task 5: Toxic Spans Detection. Our system is an ensemble of BERT-based models for binary word classification, trained on a dataset extended by toxic comments modified and generated by two language models. For the toxic word classification, the prediction threshold value was optimized separately for every comment, in order to maximize the expected F1 value.
%R 10.18653/v1/2021.semeval-1.133
%U https://aclanthology.org/2021.semeval-1.133
%U https://doi.org/10.18653/v1/2021.semeval-1.133
%P 974-983
Markdown (Informal)
[SRPOL DIALOGUE SYSTEMS at SemEval-2021 Task 5: Automatic Generation of Training Data for Toxic Spans Detection](https://aclanthology.org/2021.semeval-1.133) (Satława et al., SemEval 2021)
ACL
- Michał Satława, Katarzyna Zamłyńska, Jarosław Piersa, Joanna Kolis, Klaudia Firląg, Katarzyna Beksa, Zuzanna Bordzicka, Christian Goltz, Paweł Bujnowski, and Piotr Andruszkiewicz. 2021. SRPOL DIALOGUE SYSTEMS at SemEval-2021 Task 5: Automatic Generation of Training Data for Toxic Spans Detection. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 974–983, Online. Association for Computational Linguistics.