@inproceedings{mullick-etal-2023-content,
title = "Content Moderation for Evolving Policies using Binary Question Answering",
author = "Mullick, Sankha Subhra and
Bhambhani, Mohan and
Sinha, Suhit and
Mathur, Akshat and
Gupta, Somya and
Shah, Jidnya",
editor = "Sitaram, Sunayana and
Beigman Klebanov, Beata and
Williams, Jason D",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-industry.54",
doi = "10.18653/v1/2023.acl-industry.54",
pages = "561--573",
abstract = "Content moderation on social media is governed by policies that are intricate and frequently updated with evolving world events. However, automated content moderation systems often restrict easy adaptation to policy changes and are expected to learn policy intricacies from limited amounts of labeled data, which make effective policy compliance challenging. We propose to model content moderation as a binary question answering problem where the questions validate the loosely coupled themes constituting a policy. A decision logic is applied on top to aggregate the theme-specific validations. This way the questions pass theme information to a transformer network as explicit policy prompts, that in turn enables explainability. This setting further allows for faster adaptation to policy updates by leveraging zero-shot capabilities of pre-trained transformers. We showcase improved recall for our proposed method at 95{\textbackslash}{\%} precision on two proprietary datasets of social media posts and comments respectively annotated under curated Hate Speech and Commercial Spam policies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mullick-etal-2023-content">
<titleInfo>
<title>Content Moderation for Evolving Policies using Binary Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sankha</namePart>
<namePart type="given">Subhra</namePart>
<namePart type="family">Mullick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohan</namePart>
<namePart type="family">Bhambhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suhit</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akshat</namePart>
<namePart type="family">Mathur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Somya</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jidnya</namePart>
<namePart type="family">Shah</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 5: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beata</namePart>
<namePart type="family">Beigman Klebanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Williams</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>Content moderation on social media is governed by policies that are intricate and frequently updated with evolving world events. However, automated content moderation systems often restrict easy adaptation to policy changes and are expected to learn policy intricacies from limited amounts of labeled data, which make effective policy compliance challenging. We propose to model content moderation as a binary question answering problem where the questions validate the loosely coupled themes constituting a policy. A decision logic is applied on top to aggregate the theme-specific validations. This way the questions pass theme information to a transformer network as explicit policy prompts, that in turn enables explainability. This setting further allows for faster adaptation to policy updates by leveraging zero-shot capabilities of pre-trained transformers. We showcase improved recall for our proposed method at 95\textbackslash% precision on two proprietary datasets of social media posts and comments respectively annotated under curated Hate Speech and Commercial Spam policies.</abstract>
<identifier type="citekey">mullick-etal-2023-content</identifier>
<identifier type="doi">10.18653/v1/2023.acl-industry.54</identifier>
<location>
<url>https://aclanthology.org/2023.acl-industry.54</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>561</start>
<end>573</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Content Moderation for Evolving Policies using Binary Question Answering
%A Mullick, Sankha Subhra
%A Bhambhani, Mohan
%A Sinha, Suhit
%A Mathur, Akshat
%A Gupta, Somya
%A Shah, Jidnya
%Y Sitaram, Sunayana
%Y Beigman Klebanov, Beata
%Y Williams, Jason D.
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F mullick-etal-2023-content
%X Content moderation on social media is governed by policies that are intricate and frequently updated with evolving world events. However, automated content moderation systems often restrict easy adaptation to policy changes and are expected to learn policy intricacies from limited amounts of labeled data, which make effective policy compliance challenging. We propose to model content moderation as a binary question answering problem where the questions validate the loosely coupled themes constituting a policy. A decision logic is applied on top to aggregate the theme-specific validations. This way the questions pass theme information to a transformer network as explicit policy prompts, that in turn enables explainability. This setting further allows for faster adaptation to policy updates by leveraging zero-shot capabilities of pre-trained transformers. We showcase improved recall for our proposed method at 95\textbackslash% precision on two proprietary datasets of social media posts and comments respectively annotated under curated Hate Speech and Commercial Spam policies.
%R 10.18653/v1/2023.acl-industry.54
%U https://aclanthology.org/2023.acl-industry.54
%U https://doi.org/10.18653/v1/2023.acl-industry.54
%P 561-573
Markdown (Informal)
[Content Moderation for Evolving Policies using Binary Question Answering](https://aclanthology.org/2023.acl-industry.54) (Mullick et al., ACL 2023)
ACL
- Sankha Subhra Mullick, Mohan Bhambhani, Suhit Sinha, Akshat Mathur, Somya Gupta, and Jidnya Shah. 2023. Content Moderation for Evolving Policies using Binary Question Answering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pages 561–573, Toronto, Canada. Association for Computational Linguistics.