@inproceedings{kryscinski-etal-2022-booksum,
title = "{BOOKSUM}: A Collection of Datasets for Long-form Narrative Summarization",
author = "Kryscinski, Wojciech and
Rajani, Nazneen and
Agarwal, Divyansh and
Xiong, Caiming and
Radev, Dragomir",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.488",
doi = "10.18653/v1/2022.findings-emnlp.488",
pages = "6536--6558",
abstract = "The majority of existing text summarization datasets include short-form source documents that lack long-range causal and temporal dependencies, and often contain strong layout and stylistic biases. While relevant, such datasets will offer limited challenges for future text summarization systems. We address these issues by introducing BOOKSUM, a collection of datasets for long-form narrative summarization. Our dataset covers documents from the literature domain, such as novels, plays and stories, and includes highly abstractive, human written summaries on three levels of granularity of increasing difficulty: paragraph-, chapter-, and book-level. The domain and structure of our dataset poses a unique set of challenges for summarization systems, which include: processing very long documents, non-trivial causal and temporal dependencies, and rich discourse structures. To facilitate future work, we trained and evaluated multiple extractive and abstractive summarization models as baselines for our dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kryscinski-etal-2022-booksum">
<titleInfo>
<title>BOOKSUM: A Collection of Datasets for Long-form Narrative Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wojciech</namePart>
<namePart type="family">Kryscinski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nazneen</namePart>
<namePart type="family">Rajani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Divyansh</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caiming</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dragomir</namePart>
<namePart type="family">Radev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The majority of existing text summarization datasets include short-form source documents that lack long-range causal and temporal dependencies, and often contain strong layout and stylistic biases. While relevant, such datasets will offer limited challenges for future text summarization systems. We address these issues by introducing BOOKSUM, a collection of datasets for long-form narrative summarization. Our dataset covers documents from the literature domain, such as novels, plays and stories, and includes highly abstractive, human written summaries on three levels of granularity of increasing difficulty: paragraph-, chapter-, and book-level. The domain and structure of our dataset poses a unique set of challenges for summarization systems, which include: processing very long documents, non-trivial causal and temporal dependencies, and rich discourse structures. To facilitate future work, we trained and evaluated multiple extractive and abstractive summarization models as baselines for our dataset.</abstract>
<identifier type="citekey">kryscinski-etal-2022-booksum</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.488</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.488</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6536</start>
<end>6558</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BOOKSUM: A Collection of Datasets for Long-form Narrative Summarization
%A Kryscinski, Wojciech
%A Rajani, Nazneen
%A Agarwal, Divyansh
%A Xiong, Caiming
%A Radev, Dragomir
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F kryscinski-etal-2022-booksum
%X The majority of existing text summarization datasets include short-form source documents that lack long-range causal and temporal dependencies, and often contain strong layout and stylistic biases. While relevant, such datasets will offer limited challenges for future text summarization systems. We address these issues by introducing BOOKSUM, a collection of datasets for long-form narrative summarization. Our dataset covers documents from the literature domain, such as novels, plays and stories, and includes highly abstractive, human written summaries on three levels of granularity of increasing difficulty: paragraph-, chapter-, and book-level. The domain and structure of our dataset poses a unique set of challenges for summarization systems, which include: processing very long documents, non-trivial causal and temporal dependencies, and rich discourse structures. To facilitate future work, we trained and evaluated multiple extractive and abstractive summarization models as baselines for our dataset.
%R 10.18653/v1/2022.findings-emnlp.488
%U https://aclanthology.org/2022.findings-emnlp.488
%U https://doi.org/10.18653/v1/2022.findings-emnlp.488
%P 6536-6558
Markdown (Informal)
[BOOKSUM: A Collection of Datasets for Long-form Narrative Summarization](https://aclanthology.org/2022.findings-emnlp.488) (Kryscinski et al., Findings 2022)
ACL