@inproceedings{chun-2024-aistorysimilarity,
title = "{AIS}tory{S}imilarity: Quantifying Story Similarity Using Narrative for Search, {IP} Infringement, and Guided Creativity",
author = "Chun, Jon",
editor = "Barak, Libby and
Alikhani, Malihe",
booktitle = "Proceedings of the 28th Conference on Computational Natural Language Learning",
month = nov,
year = "2024",
address = "Miami, FL, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.conll-1.13",
pages = "161--177",
abstract = "Stories are central for interpreting experiences, communicating, and influencing each other via films, medical, media, and other narratives. Quantifying the similarity between stories has numerous applications including detecting IP infringement, detecting hallucinations, search/recommendation engines, and guiding human-AI collaborations. Despite this, traditional NLP text similarity metrics are limited to short text distance metrics like n-gram overlaps and embeddings. Larger texts require preprocessing with significant information loss through paraphrasing or multi-step decomposition. This paper introduces AIStorySimilarity, a novel benchmark to measure the semantic distance between long-text stories based on core structural elements drawn from narrative theory and script writing. Based on four narrative elements (characters, plot, setting, and themes) as well 31 sub-features within these, we use a SOTA LLM (gpt-3.5-turbo) to extract and evaluate the semantic similarity of a diverse set of major Hollywood movies. In addition, we compare human evaluation with story similarity scores computed three ways: extracting elements from film scripts before evaluation (Elements), directly evaluating entire scripts (Scripts), and extracting narrative elements from the parametric memory of SOTA LLMs without any provided scripts (GenAI). To the best of our knowledge, AIStorySimilarity is the first benchmark to measure long-text story similarity using a comprehensive approach to narrative theory. Code and data are available at https://github.com/jon-chun/AIStorySimiliarity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chun-2024-aistorysimilarity">
<titleInfo>
<title>AIStorySimilarity: Quantifying Story Similarity Using Narrative for Search, IP Infringement, and Guided Creativity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jon</namePart>
<namePart type="family">Chun</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 28th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Libby</namePart>
<namePart type="family">Barak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, FL, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Stories are central for interpreting experiences, communicating, and influencing each other via films, medical, media, and other narratives. Quantifying the similarity between stories has numerous applications including detecting IP infringement, detecting hallucinations, search/recommendation engines, and guiding human-AI collaborations. Despite this, traditional NLP text similarity metrics are limited to short text distance metrics like n-gram overlaps and embeddings. Larger texts require preprocessing with significant information loss through paraphrasing or multi-step decomposition. This paper introduces AIStorySimilarity, a novel benchmark to measure the semantic distance between long-text stories based on core structural elements drawn from narrative theory and script writing. Based on four narrative elements (characters, plot, setting, and themes) as well 31 sub-features within these, we use a SOTA LLM (gpt-3.5-turbo) to extract and evaluate the semantic similarity of a diverse set of major Hollywood movies. In addition, we compare human evaluation with story similarity scores computed three ways: extracting elements from film scripts before evaluation (Elements), directly evaluating entire scripts (Scripts), and extracting narrative elements from the parametric memory of SOTA LLMs without any provided scripts (GenAI). To the best of our knowledge, AIStorySimilarity is the first benchmark to measure long-text story similarity using a comprehensive approach to narrative theory. Code and data are available at https://github.com/jon-chun/AIStorySimiliarity.</abstract>
<identifier type="citekey">chun-2024-aistorysimilarity</identifier>
<location>
<url>https://aclanthology.org/2024.conll-1.13</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>161</start>
<end>177</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AIStorySimilarity: Quantifying Story Similarity Using Narrative for Search, IP Infringement, and Guided Creativity
%A Chun, Jon
%Y Barak, Libby
%Y Alikhani, Malihe
%S Proceedings of the 28th Conference on Computational Natural Language Learning
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, FL, USA
%F chun-2024-aistorysimilarity
%X Stories are central for interpreting experiences, communicating, and influencing each other via films, medical, media, and other narratives. Quantifying the similarity between stories has numerous applications including detecting IP infringement, detecting hallucinations, search/recommendation engines, and guiding human-AI collaborations. Despite this, traditional NLP text similarity metrics are limited to short text distance metrics like n-gram overlaps and embeddings. Larger texts require preprocessing with significant information loss through paraphrasing or multi-step decomposition. This paper introduces AIStorySimilarity, a novel benchmark to measure the semantic distance between long-text stories based on core structural elements drawn from narrative theory and script writing. Based on four narrative elements (characters, plot, setting, and themes) as well 31 sub-features within these, we use a SOTA LLM (gpt-3.5-turbo) to extract and evaluate the semantic similarity of a diverse set of major Hollywood movies. In addition, we compare human evaluation with story similarity scores computed three ways: extracting elements from film scripts before evaluation (Elements), directly evaluating entire scripts (Scripts), and extracting narrative elements from the parametric memory of SOTA LLMs without any provided scripts (GenAI). To the best of our knowledge, AIStorySimilarity is the first benchmark to measure long-text story similarity using a comprehensive approach to narrative theory. Code and data are available at https://github.com/jon-chun/AIStorySimiliarity.
%U https://aclanthology.org/2024.conll-1.13
%P 161-177
Markdown (Informal)
[AIStorySimilarity: Quantifying Story Similarity Using Narrative for Search, IP Infringement, and Guided Creativity](https://aclanthology.org/2024.conll-1.13) (Chun, CoNLL 2024)
ACL