@inproceedings{pu-etal-2022-two,
title = "Two-Stage Movie Script Summarization: An Efficient Method For Low-Resource Long Document Summarization",
author = "Pu, Dongqi and
Hong, Xudong and
Lin, Pin-Jie and
Chang, Ernie and
Demberg, Vera",
editor = "Mckeown, Kathleen",
booktitle = "Proceedings of The Workshop on Automatic Summarization for Creative Writing",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.creativesumm-1.9",
pages = "57--66",
abstract = "The Creative Summarization Shared Task at COLING 2022 aspires to generate summaries given long-form texts from creative writing. This paper presents the system architecture and the results of our participation in the Scriptbase track that focuses on generating movie plots given movie scripts. The core innovation in our model employs a two-stage hierarchical architecture for movie script summarization. In the first stage, a heuristic extraction method is applied to extract actions and essential dialogues, which reduces the average length of input movie scripts by 66{\%} from about 24K to 8K tokens. In the second stage, a state-of-the-art encoder-decoder model, Longformer-Encoder-Decoder (LED), is trained with effective fine-tuning methods, BitFit and NoisyTune. Evaluations on the unseen test set indicate that our system outperforms both zero-shot LED baselines as well as other participants on various automatic metrics and ranks 1st in the Scriptbase track.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pu-etal-2022-two">
<titleInfo>
<title>Two-Stage Movie Script Summarization: An Efficient Method For Low-Resource Long Document Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongqi</namePart>
<namePart type="family">Pu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xudong</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pin-Jie</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ernie</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Workshop on Automatic Summarization for Creative Writing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kathleen</namePart>
<namePart type="family">Mckeown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Creative Summarization Shared Task at COLING 2022 aspires to generate summaries given long-form texts from creative writing. This paper presents the system architecture and the results of our participation in the Scriptbase track that focuses on generating movie plots given movie scripts. The core innovation in our model employs a two-stage hierarchical architecture for movie script summarization. In the first stage, a heuristic extraction method is applied to extract actions and essential dialogues, which reduces the average length of input movie scripts by 66% from about 24K to 8K tokens. In the second stage, a state-of-the-art encoder-decoder model, Longformer-Encoder-Decoder (LED), is trained with effective fine-tuning methods, BitFit and NoisyTune. Evaluations on the unseen test set indicate that our system outperforms both zero-shot LED baselines as well as other participants on various automatic metrics and ranks 1st in the Scriptbase track.</abstract>
<identifier type="citekey">pu-etal-2022-two</identifier>
<location>
<url>https://aclanthology.org/2022.creativesumm-1.9</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>57</start>
<end>66</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Two-Stage Movie Script Summarization: An Efficient Method For Low-Resource Long Document Summarization
%A Pu, Dongqi
%A Hong, Xudong
%A Lin, Pin-Jie
%A Chang, Ernie
%A Demberg, Vera
%Y Mckeown, Kathleen
%S Proceedings of The Workshop on Automatic Summarization for Creative Writing
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F pu-etal-2022-two
%X The Creative Summarization Shared Task at COLING 2022 aspires to generate summaries given long-form texts from creative writing. This paper presents the system architecture and the results of our participation in the Scriptbase track that focuses on generating movie plots given movie scripts. The core innovation in our model employs a two-stage hierarchical architecture for movie script summarization. In the first stage, a heuristic extraction method is applied to extract actions and essential dialogues, which reduces the average length of input movie scripts by 66% from about 24K to 8K tokens. In the second stage, a state-of-the-art encoder-decoder model, Longformer-Encoder-Decoder (LED), is trained with effective fine-tuning methods, BitFit and NoisyTune. Evaluations on the unseen test set indicate that our system outperforms both zero-shot LED baselines as well as other participants on various automatic metrics and ranks 1st in the Scriptbase track.
%U https://aclanthology.org/2022.creativesumm-1.9
%P 57-66
Markdown (Informal)
[Two-Stage Movie Script Summarization: An Efficient Method For Low-Resource Long Document Summarization](https://aclanthology.org/2022.creativesumm-1.9) (Pu et al., CreativeSumm 2022)
ACL