@inproceedings{saxena-keller-2024-moviesum,
title = "{M}ovie{S}um: An Abstractive Summarization Dataset for Movie Screenplays",
author = "Saxena, Rohit and
Keller, Frank",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.239",
doi = "10.18653/v1/2024.findings-acl.239",
pages = "4043--4050",
abstract = "Movie screenplay summarization is challenging, as it requires an understanding of long input contexts and various elements unique to movies. Large language models have shown significant advancements in document summarization, but they often struggle with processing long input contexts. Furthermore, while television transcripts have received attention in recent studies, movie screenplay summarization remains underexplored. To stimulate research in this area, we present a new dataset, MovieSum, for abstractive summarization of movie screenplays. This dataset comprises 2200 movie screenplays accompanied by their Wikipedia plot summaries. We manually formatted the movie screenplays to represent their structural elements. Compared to existing datasets, MovieSum possesses several distinctive features: 1) It includes movie screenplays which are longer than scripts of TV episodes. 2) It is twice the size of previous movie screenplay datasets. 3) It provides metadata with IMDb IDs to facilitate access to additional external knowledge. We also show the results of recently released large language models applied to summarization on our dataset to provide a detailed baseline.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saxena-keller-2024-moviesum">
<titleInfo>
<title>MovieSum: An Abstractive Summarization Dataset for Movie Screenplays</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rohit</namePart>
<namePart type="family">Saxena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Keller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Movie screenplay summarization is challenging, as it requires an understanding of long input contexts and various elements unique to movies. Large language models have shown significant advancements in document summarization, but they often struggle with processing long input contexts. Furthermore, while television transcripts have received attention in recent studies, movie screenplay summarization remains underexplored. To stimulate research in this area, we present a new dataset, MovieSum, for abstractive summarization of movie screenplays. This dataset comprises 2200 movie screenplays accompanied by their Wikipedia plot summaries. We manually formatted the movie screenplays to represent their structural elements. Compared to existing datasets, MovieSum possesses several distinctive features: 1) It includes movie screenplays which are longer than scripts of TV episodes. 2) It is twice the size of previous movie screenplay datasets. 3) It provides metadata with IMDb IDs to facilitate access to additional external knowledge. We also show the results of recently released large language models applied to summarization on our dataset to provide a detailed baseline.</abstract>
<identifier type="citekey">saxena-keller-2024-moviesum</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.239</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.239</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>4043</start>
<end>4050</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MovieSum: An Abstractive Summarization Dataset for Movie Screenplays
%A Saxena, Rohit
%A Keller, Frank
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F saxena-keller-2024-moviesum
%X Movie screenplay summarization is challenging, as it requires an understanding of long input contexts and various elements unique to movies. Large language models have shown significant advancements in document summarization, but they often struggle with processing long input contexts. Furthermore, while television transcripts have received attention in recent studies, movie screenplay summarization remains underexplored. To stimulate research in this area, we present a new dataset, MovieSum, for abstractive summarization of movie screenplays. This dataset comprises 2200 movie screenplays accompanied by their Wikipedia plot summaries. We manually formatted the movie screenplays to represent their structural elements. Compared to existing datasets, MovieSum possesses several distinctive features: 1) It includes movie screenplays which are longer than scripts of TV episodes. 2) It is twice the size of previous movie screenplay datasets. 3) It provides metadata with IMDb IDs to facilitate access to additional external knowledge. We also show the results of recently released large language models applied to summarization on our dataset to provide a detailed baseline.
%R 10.18653/v1/2024.findings-acl.239
%U https://aclanthology.org/2024.findings-acl.239
%U https://doi.org/10.18653/v1/2024.findings-acl.239
%P 4043-4050
Markdown (Informal)
[MovieSum: An Abstractive Summarization Dataset for Movie Screenplays](https://aclanthology.org/2024.findings-acl.239) (Saxena & Keller, Findings 2024)
ACL