@inproceedings{tu-etal-2022-uper,
title = "{UPER}: Boosting Multi-Document Summarization with an Unsupervised Prompt-based Extractor",
author = "Tu, Shangqing and
Yu, Jifan and
Zhu, Fangwei and
Li, Juanzi and
Hou, Lei and
Nie, Jian-Yun",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.550",
pages = "6315--6326",
abstract = "Multi-Document Summarization (MDS) commonly employs the 2-stage extract-then-abstract paradigm, which first extracts a relatively short meta-document, then feeds it into the deep neural networks to generate an abstract. Previous work usually takes the ROUGE score as the label for training a scoring model to evaluate source documents. However, the trained scoring model is prone to under-fitting for low-resource settings, as it relies on the training data. To extract documents effectively, we construct prompting templates that invoke the underlying knowledge in Pre-trained Language Model (PLM) to calculate the document and keyword{'}s perplexity, which can assess the document{'}s semantic salience. Our unsupervised approach can be applied as a plug-in to boost other metrics for evaluating a document{'}s salience, thus improving the subsequent abstract generation. We get positive results on 2 MDS datasets, 2 data settings, and 2 abstractive backbone models, showing our method{'}s effectiveness. Our code is available at \url{https://github.com/THU-KEG/UPER}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tu-etal-2022-uper">
<titleInfo>
<title>UPER: Boosting Multi-Document Summarization with an Unsupervised Prompt-based Extractor</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shangqing</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jifan</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fangwei</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juanzi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian-Yun</namePart>
<namePart type="family">Nie</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 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-Document Summarization (MDS) commonly employs the 2-stage extract-then-abstract paradigm, which first extracts a relatively short meta-document, then feeds it into the deep neural networks to generate an abstract. Previous work usually takes the ROUGE score as the label for training a scoring model to evaluate source documents. However, the trained scoring model is prone to under-fitting for low-resource settings, as it relies on the training data. To extract documents effectively, we construct prompting templates that invoke the underlying knowledge in Pre-trained Language Model (PLM) to calculate the document and keyword’s perplexity, which can assess the document’s semantic salience. Our unsupervised approach can be applied as a plug-in to boost other metrics for evaluating a document’s salience, thus improving the subsequent abstract generation. We get positive results on 2 MDS datasets, 2 data settings, and 2 abstractive backbone models, showing our method’s effectiveness. Our code is available at https://github.com/THU-KEG/UPER</abstract>
<identifier type="citekey">tu-etal-2022-uper</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.550</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>6315</start>
<end>6326</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UPER: Boosting Multi-Document Summarization with an Unsupervised Prompt-based Extractor
%A Tu, Shangqing
%A Yu, Jifan
%A Zhu, Fangwei
%A Li, Juanzi
%A Hou, Lei
%A Nie, Jian-Yun
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F tu-etal-2022-uper
%X Multi-Document Summarization (MDS) commonly employs the 2-stage extract-then-abstract paradigm, which first extracts a relatively short meta-document, then feeds it into the deep neural networks to generate an abstract. Previous work usually takes the ROUGE score as the label for training a scoring model to evaluate source documents. However, the trained scoring model is prone to under-fitting for low-resource settings, as it relies on the training data. To extract documents effectively, we construct prompting templates that invoke the underlying knowledge in Pre-trained Language Model (PLM) to calculate the document and keyword’s perplexity, which can assess the document’s semantic salience. Our unsupervised approach can be applied as a plug-in to boost other metrics for evaluating a document’s salience, thus improving the subsequent abstract generation. We get positive results on 2 MDS datasets, 2 data settings, and 2 abstractive backbone models, showing our method’s effectiveness. Our code is available at https://github.com/THU-KEG/UPER
%U https://aclanthology.org/2022.coling-1.550
%P 6315-6326
Markdown (Informal)
[UPER: Boosting Multi-Document Summarization with an Unsupervised Prompt-based Extractor](https://aclanthology.org/2022.coling-1.550) (Tu et al., COLING 2022)
ACL