<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chali-egonmwan-2024-transfer-learning">
    <titleInfo>
        <title>Transfer-Learning based on Extract, Paraphrase and Compress Models for Neural Abstractive Multi-Document Summarization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yllias</namePart>
        <namePart type="family">Chali</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Elozino</namePart>
        <namePart type="family">Egonmwan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th International Natural Language Generation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Saad</namePart>
            <namePart type="family">Mahamood</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nguyen</namePart>
            <namePart type="given">Le</namePart>
            <namePart type="family">Minh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Daphne</namePart>
            <namePart type="family">Ippolito</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Tokyo, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recently, transfer-learning by unsupervised pre-training and fine-tuning has shown great success on a number of tasks. The paucity of data for multi-document summarization (MDS) in the news domain, especially makes this approach practical. However, while existing literature mostly formulate unsupervised learning objectives tailored for/around the summarization problem we find that MDS can benefit directly from models pre-trained on other downstream supervised tasks such as sentence extraction, paraphrase generation and sentence compression. We carry out experiments to demonstrate the impact of zero-shot transfer-learning from these downstream tasks on MDS. Since it is challenging to train end-to-end encoder-decoder models on MDS due to i) the sheer length of the input documents, and ii) the paucity of training data. We hope this paper encourages more work on these downstream tasks as a means to mitigating the challenges in neural abstractive MDS.</abstract>
    <identifier type="citekey">chali-egonmwan-2024-transfer-learning</identifier>
    <location>
        <url>https://aclanthology.org/2024.inlg-main.17</url>
    </location>
    <part>
        <date>2024-09</date>
        <extent unit="page">
            <start>213</start>
            <end>221</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Transfer-Learning based on Extract, Paraphrase and Compress Models for Neural Abstractive Multi-Document Summarization
%A Chali, Yllias
%A Egonmwan, Elozino
%Y Mahamood, Saad
%Y Minh, Nguyen Le
%Y Ippolito, Daphne
%S Proceedings of the 17th International Natural Language Generation Conference
%D 2024
%8 September
%I Association for Computational Linguistics
%C Tokyo, Japan
%F chali-egonmwan-2024-transfer-learning
%X Recently, transfer-learning by unsupervised pre-training and fine-tuning has shown great success on a number of tasks. The paucity of data for multi-document summarization (MDS) in the news domain, especially makes this approach practical. However, while existing literature mostly formulate unsupervised learning objectives tailored for/around the summarization problem we find that MDS can benefit directly from models pre-trained on other downstream supervised tasks such as sentence extraction, paraphrase generation and sentence compression. We carry out experiments to demonstrate the impact of zero-shot transfer-learning from these downstream tasks on MDS. Since it is challenging to train end-to-end encoder-decoder models on MDS due to i) the sheer length of the input documents, and ii) the paucity of training data. We hope this paper encourages more work on these downstream tasks as a means to mitigating the challenges in neural abstractive MDS.
%U https://aclanthology.org/2024.inlg-main.17
%P 213-221

Markdown (Informal)

[Transfer-Learning based on Extract, Paraphrase and Compress Models for Neural Abstractive Multi-Document Summarization](https://aclanthology.org/2024.inlg-main.17) (Chali & Egonmwan, INLG 2024)

• Transfer-Learning based on Extract, Paraphrase and Compress Models for Neural Abstractive Multi-Document Summarization (Chali & Egonmwan, INLG 2024)

ACL

• Yllias Chali and Elozino Egonmwan. 2024. Transfer-Learning based on Extract, Paraphrase and Compress Models for Neural Abstractive Multi-Document Summarization. In Proceedings of the 17th International Natural Language Generation Conference, pages 213–221, Tokyo, Japan. Association for Computational Linguistics.