<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lam-etal-2023-abstractive">
    <titleInfo>
        <title>Abstractive Text Summarization Using the BRIO Training Paradigm</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Khang</namePart>
        <namePart type="family">Lam</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thieu</namePart>
        <namePart type="family">Doan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Khang</namePart>
        <namePart type="family">Pham</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jugal</namePart>
        <namePart type="family">Kalita</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Summary sentences produced by abstractive summarization models may be coherent and comprehensive, but they lack control and rely heavily on reference summaries. The BRIO training paradigm assumes a non-deterministic distribution to reduce the model’s dependence on reference summaries, and improve model performance during inference. This paper presents a straightforward but effective technique to improve abstractive summaries by fine-tuning pre-trained language models, and training them with the BRIO paradigm. We build a text summarization dataset for Vietnamese, called VieSum. We perform experiments with abstractive summarization models trained with the BRIO paradigm on the CNNDM and the VieSum datasets. The results show that the models, trained on basic hardware, outperform all existing abstractive summarization models, especially for Vietnamese.</abstract>
    <identifier type="citekey">lam-etal-2023-abstractive</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.7</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.7</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>92</start>
            <end>99</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Abstractive Text Summarization Using the BRIO Training Paradigm
%A Lam, Khang
%A Doan, Thieu
%A Pham, Khang
%A Kalita, Jugal
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F lam-etal-2023-abstractive
%X Summary sentences produced by abstractive summarization models may be coherent and comprehensive, but they lack control and rely heavily on reference summaries. The BRIO training paradigm assumes a non-deterministic distribution to reduce the model’s dependence on reference summaries, and improve model performance during inference. This paper presents a straightforward but effective technique to improve abstractive summaries by fine-tuning pre-trained language models, and training them with the BRIO paradigm. We build a text summarization dataset for Vietnamese, called VieSum. We perform experiments with abstractive summarization models trained with the BRIO paradigm on the CNNDM and the VieSum datasets. The results show that the models, trained on basic hardware, outperform all existing abstractive summarization models, especially for Vietnamese.
%R 10.18653/v1/2023.findings-acl.7
%U https://aclanthology.org/2023.findings-acl.7
%U https://doi.org/10.18653/v1/2023.findings-acl.7
%P 92-99

Markdown (Informal)

[Abstractive Text Summarization Using the BRIO Training Paradigm](https://aclanthology.org/2023.findings-acl.7) (Lam et al., Findings 2023)

• Abstractive Text Summarization Using the BRIO Training Paradigm (Lam et al., Findings 2023)

ACL

• Khang Lam, Thieu Doan, Khang Pham, and Jugal Kalita. 2023. Abstractive Text Summarization Using the BRIO Training Paradigm. In Findings of the Association for Computational Linguistics: ACL 2023, pages 92–99, Toronto, Canada. Association for Computational Linguistics.