@inproceedings{wiegmann-etal-2023-trigger,
title = "Trigger Warning Assignment as a Multi-Label Document Classification Problem",
author = {Wiegmann, Matti and
Wolska, Magdalena and
Schr{\"o}der, Christopher and
Borchardt, Ole and
Stein, Benno and
Potthast, Martin},
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.676",
doi = "10.18653/v1/2023.acl-long.676",
pages = "12113--12134",
abstract = "A trigger warning is used to warn people about potentially disturbing content. We introduce trigger warning assignment as a multi-label classification task, create the Webis Trigger Warning Corpus 2022, and with it the first dataset of 1 million fanfiction works from Archive of our Own with up to 36 different warnings per document. To provide a reliable catalog of trigger warnings, we organized 41 million of free-form tags assigned by fanfiction authors into the first comprehensive taxonomy of trigger warnings by mapping them to the 36 institutionally recommended warnings. To determine the best operationalization of trigger warnings, we explore state-of-the-art multi-label models, examining the trade-off between assigning coarse- and fine-grained warnings, open- and closed-set classification, document length, and label confidence. Our models achieve micro-F1 scores of about 0.5, which reveals the difficulty of the task. Tailored representations, long input sequences, and a higher recall on rare warnings would help.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wiegmann-etal-2023-trigger">
<titleInfo>
<title>Trigger Warning Assignment as a Multi-Label Document Classification Problem</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matti</namePart>
<namePart type="family">Wiegmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magdalena</namePart>
<namePart type="family">Wolska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Schröder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ole</namePart>
<namePart type="family">Borchardt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benno</namePart>
<namePart type="family">Stein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Potthast</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A trigger warning is used to warn people about potentially disturbing content. We introduce trigger warning assignment as a multi-label classification task, create the Webis Trigger Warning Corpus 2022, and with it the first dataset of 1 million fanfiction works from Archive of our Own with up to 36 different warnings per document. To provide a reliable catalog of trigger warnings, we organized 41 million of free-form tags assigned by fanfiction authors into the first comprehensive taxonomy of trigger warnings by mapping them to the 36 institutionally recommended warnings. To determine the best operationalization of trigger warnings, we explore state-of-the-art multi-label models, examining the trade-off between assigning coarse- and fine-grained warnings, open- and closed-set classification, document length, and label confidence. Our models achieve micro-F1 scores of about 0.5, which reveals the difficulty of the task. Tailored representations, long input sequences, and a higher recall on rare warnings would help.</abstract>
<identifier type="citekey">wiegmann-etal-2023-trigger</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.676</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.676</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>12113</start>
<end>12134</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Trigger Warning Assignment as a Multi-Label Document Classification Problem
%A Wiegmann, Matti
%A Wolska, Magdalena
%A Schröder, Christopher
%A Borchardt, Ole
%A Stein, Benno
%A Potthast, Martin
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wiegmann-etal-2023-trigger
%X A trigger warning is used to warn people about potentially disturbing content. We introduce trigger warning assignment as a multi-label classification task, create the Webis Trigger Warning Corpus 2022, and with it the first dataset of 1 million fanfiction works from Archive of our Own with up to 36 different warnings per document. To provide a reliable catalog of trigger warnings, we organized 41 million of free-form tags assigned by fanfiction authors into the first comprehensive taxonomy of trigger warnings by mapping them to the 36 institutionally recommended warnings. To determine the best operationalization of trigger warnings, we explore state-of-the-art multi-label models, examining the trade-off between assigning coarse- and fine-grained warnings, open- and closed-set classification, document length, and label confidence. Our models achieve micro-F1 scores of about 0.5, which reveals the difficulty of the task. Tailored representations, long input sequences, and a higher recall on rare warnings would help.
%R 10.18653/v1/2023.acl-long.676
%U https://aclanthology.org/2023.acl-long.676
%U https://doi.org/10.18653/v1/2023.acl-long.676
%P 12113-12134
Markdown (Informal)
[Trigger Warning Assignment as a Multi-Label Document Classification Problem](https://aclanthology.org/2023.acl-long.676) (Wiegmann et al., ACL 2023)
ACL
- Matti Wiegmann, Magdalena Wolska, Christopher Schröder, Ole Borchardt, Benno Stein, and Martin Potthast. 2023. Trigger Warning Assignment as a Multi-Label Document Classification Problem. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12113–12134, Toronto, Canada. Association for Computational Linguistics.