@inproceedings{tsai-etal-2024-pg,
title = "{PG}-Story: Taxonomy, Dataset, and Evaluation for Ensuring Child-Safe Content for Story Generation",
author = "Tsai, Alicia Y. and
Oraby, Shereen and
Narayan-Chen, Anjali and
Cervone, Alessandra and
Gella, Spandana and
Verma, Apurv and
Chung, Tagyoung and
Huang, Jing and
Peng, Nanyun",
editor = "Dementieva, Daryna and
Ignat, Oana and
Jin, Zhijing and
Mihalcea, Rada and
Piatti, Giorgio and
Tetreault, Joel and
Wilson, Steven and
Zhao, Jieyu",
booktitle = "Proceedings of the Third Workshop on NLP for Positive Impact",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nlp4pi-1.7",
pages = "78--97",
abstract = "Creating children{'}s stories through text generation is a creative task that requires stories to be both entertaining and suitable for young audiences. However, since current story generation systems often rely on pre-trained language models fine-tuned with limited story data, they may not always prioritize child-friendliness. This can lead to the unintended generation of stories containing problematic elements such as violence, profanity, and biases. Regrettably, despite the significance of these concerns, there is a lack of clear guidelines and benchmark datasets for ensuring content safety for children. In this paper, we introduce a taxonomy specifically tailored to assess content safety in text, with a strong emphasis on children{'}s well-being. We present PG-Story, a dataset that includes detailed annotations for both sentence-level and discourse-level safety. We demonstrate the potential of identifying unsafe content through self-diagnosis and employing controllable generation techniques during the decoding phase to minimize unsafe elements in generated stories.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tsai-etal-2024-pg">
<titleInfo>
<title>PG-Story: Taxonomy, Dataset, and Evaluation for Ensuring Child-Safe Content for Story Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="given">Y</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shereen</namePart>
<namePart type="family">Oraby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anjali</namePart>
<namePart type="family">Narayan-Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandra</namePart>
<namePart type="family">Cervone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apurv</namePart>
<namePart type="family">Verma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tagyoung</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on NLP for Positive Impact</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daryna</namePart>
<namePart type="family">Dementieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana</namePart>
<namePart type="family">Ignat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhijing</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giorgio</namePart>
<namePart type="family">Piatti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Wilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Creating children’s stories through text generation is a creative task that requires stories to be both entertaining and suitable for young audiences. However, since current story generation systems often rely on pre-trained language models fine-tuned with limited story data, they may not always prioritize child-friendliness. This can lead to the unintended generation of stories containing problematic elements such as violence, profanity, and biases. Regrettably, despite the significance of these concerns, there is a lack of clear guidelines and benchmark datasets for ensuring content safety for children. In this paper, we introduce a taxonomy specifically tailored to assess content safety in text, with a strong emphasis on children’s well-being. We present PG-Story, a dataset that includes detailed annotations for both sentence-level and discourse-level safety. We demonstrate the potential of identifying unsafe content through self-diagnosis and employing controllable generation techniques during the decoding phase to minimize unsafe elements in generated stories.</abstract>
<identifier type="citekey">tsai-etal-2024-pg</identifier>
<location>
<url>https://aclanthology.org/2024.nlp4pi-1.7</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>78</start>
<end>97</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PG-Story: Taxonomy, Dataset, and Evaluation for Ensuring Child-Safe Content for Story Generation
%A Tsai, Alicia Y.
%A Oraby, Shereen
%A Narayan-Chen, Anjali
%A Cervone, Alessandra
%A Gella, Spandana
%A Verma, Apurv
%A Chung, Tagyoung
%A Huang, Jing
%A Peng, Nanyun
%Y Dementieva, Daryna
%Y Ignat, Oana
%Y Jin, Zhijing
%Y Mihalcea, Rada
%Y Piatti, Giorgio
%Y Tetreault, Joel
%Y Wilson, Steven
%Y Zhao, Jieyu
%S Proceedings of the Third Workshop on NLP for Positive Impact
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F tsai-etal-2024-pg
%X Creating children’s stories through text generation is a creative task that requires stories to be both entertaining and suitable for young audiences. However, since current story generation systems often rely on pre-trained language models fine-tuned with limited story data, they may not always prioritize child-friendliness. This can lead to the unintended generation of stories containing problematic elements such as violence, profanity, and biases. Regrettably, despite the significance of these concerns, there is a lack of clear guidelines and benchmark datasets for ensuring content safety for children. In this paper, we introduce a taxonomy specifically tailored to assess content safety in text, with a strong emphasis on children’s well-being. We present PG-Story, a dataset that includes detailed annotations for both sentence-level and discourse-level safety. We demonstrate the potential of identifying unsafe content through self-diagnosis and employing controllable generation techniques during the decoding phase to minimize unsafe elements in generated stories.
%U https://aclanthology.org/2024.nlp4pi-1.7
%P 78-97
Markdown (Informal)
[PG-Story: Taxonomy, Dataset, and Evaluation for Ensuring Child-Safe Content for Story Generation](https://aclanthology.org/2024.nlp4pi-1.7) (Tsai et al., NLP4PI 2024)
ACL
- Alicia Y. Tsai, Shereen Oraby, Anjali Narayan-Chen, Alessandra Cervone, Spandana Gella, Apurv Verma, Tagyoung Chung, Jing Huang, and Nanyun Peng. 2024. PG-Story: Taxonomy, Dataset, and Evaluation for Ensuring Child-Safe Content for Story Generation. In Proceedings of the Third Workshop on NLP for Positive Impact, pages 78–97, Miami, Florida, USA. Association for Computational Linguistics.