<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lebanoff-etal-2021-modeling">
    <titleInfo>
        <title>Modeling Endorsement for Multi-Document Abstractive Summarization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Logan</namePart>
        <namePart type="family">Lebanoff</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bingqing</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhe</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fei</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Third Workshop on New Frontiers in Summarization</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Giuseppe</namePart>
            <namePart type="family">Carenini</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jackie</namePart>
            <namePart type="given">Chi</namePart>
            <namePart type="given">Kit</namePart>
            <namePart type="family">Cheung</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Dong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Fei</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lu</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and in Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>A crucial difference between single- and multi-document summarization is how salient content manifests itself in the document(s). While such content may appear at the beginning of a single document, essential information is frequently reiterated in a set of documents related to a particular topic, resulting in an endorsement effect that increases information salience. In this paper, we model the cross-document endorsement effect and its utilization in multiple document summarization. Our method generates a synopsis from each document, which serves as an endorser to identify salient content from other documents. Strongly endorsed text segments are used to enrich a neural encoder-decoder model to consolidate them into an abstractive summary. The method has a great potential to learn from fewer examples to identify salient content, which alleviates the need for costly retraining when the set of documents is dynamically adjusted. Through extensive experiments on benchmark multi-document summarization datasets, we demonstrate the effectiveness of our proposed method over strong published baselines. Finally, we shed light on future research directions and discuss broader challenges of this task using a case study.</abstract>
    <identifier type="citekey">lebanoff-etal-2021-modeling</identifier>
    <identifier type="doi">10.18653/v1/2021.newsum-1.13</identifier>
    <location>
        <url>https://aclanthology.org/2021.newsum-1.13</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>119</start>
            <end>130</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Modeling Endorsement for Multi-Document Abstractive Summarization
%A Lebanoff, Logan
%A Wang, Bingqing
%A Feng, Zhe
%A Liu, Fei
%Y Carenini, Giuseppe
%Y Cheung, Jackie Chi Kit
%Y Dong, Yue
%Y Liu, Fei
%Y Wang, Lu
%S Proceedings of the Third Workshop on New Frontiers in Summarization
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and in Dominican Republic
%F lebanoff-etal-2021-modeling
%X A crucial difference between single- and multi-document summarization is how salient content manifests itself in the document(s). While such content may appear at the beginning of a single document, essential information is frequently reiterated in a set of documents related to a particular topic, resulting in an endorsement effect that increases information salience. In this paper, we model the cross-document endorsement effect and its utilization in multiple document summarization. Our method generates a synopsis from each document, which serves as an endorser to identify salient content from other documents. Strongly endorsed text segments are used to enrich a neural encoder-decoder model to consolidate them into an abstractive summary. The method has a great potential to learn from fewer examples to identify salient content, which alleviates the need for costly retraining when the set of documents is dynamically adjusted. Through extensive experiments on benchmark multi-document summarization datasets, we demonstrate the effectiveness of our proposed method over strong published baselines. Finally, we shed light on future research directions and discuss broader challenges of this task using a case study.
%R 10.18653/v1/2021.newsum-1.13
%U https://aclanthology.org/2021.newsum-1.13
%U https://doi.org/10.18653/v1/2021.newsum-1.13
%P 119-130

Markdown (Informal)

[Modeling Endorsement for Multi-Document Abstractive Summarization](https://aclanthology.org/2021.newsum-1.13) (Lebanoff et al., NewSum 2021)

• Modeling Endorsement for Multi-Document Abstractive Summarization (Lebanoff et al., NewSum 2021)

ACL

• Logan Lebanoff, Bingqing Wang, Zhe Feng, and Fei Liu. 2021. Modeling Endorsement for Multi-Document Abstractive Summarization. In Proceedings of the Third Workshop on New Frontiers in Summarization, pages 119–130, Online and in Dominican Republic. Association for Computational Linguistics.