<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="angelidis-etal-2021-extractive">
    <titleInfo>
        <title>Extractive Opinion Summarization in Quantized Transformer Spaces</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Stefanos</namePart>
        <namePart type="family">Angelidis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Reinald</namePart>
        <namePart type="given">Kim</namePart>
        <namePart type="family">Amplayo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yoshihiko</namePart>
        <namePart type="family">Suhara</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaolan</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mirella</namePart>
        <namePart type="family">Lapata</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>We present the Quantized Transformer (QT), an unsupervised system for extractive opinion summarization. QT is inspired by Vector- Quantized Variational Autoencoders, which we repurpose for popularity-driven summarization. It uses a clustering interpretation of the quantized space and a novel extraction algorithm to discover popular opinions among hundreds of reviews, a significant step towards opinion summarization of practical scope. In addition, QT enables controllable summarization without further training, by utilizing properties of the quantized space to extract aspect-specific summaries. We also make publicly available Space, a large-scale evaluation benchmark for opinion summarizers, comprising general and aspect-specific summaries for 50 hotels. Experiments demonstrate the promise of our approach, which is validated by human studies where judges showed clear preference for our method over competitive baselines.</abstract>
    <identifier type="citekey">angelidis-etal-2021-extractive</identifier>
    <identifier type="doi">10.1162/tacl_a_00366</identifier>
    <location>
        <url>https://aclanthology.org/2021.tacl-1.17</url>
    </location>
    <part>
        <date>2021</date>
        <detail type="volume"><number>9</number></detail>
        <extent unit="page">
            <start>277</start>
            <end>293</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Extractive Opinion Summarization in Quantized Transformer Spaces
%A Angelidis, Stefanos
%A Amplayo, Reinald Kim
%A Suhara, Yoshihiko
%A Wang, Xiaolan
%A Lapata, Mirella
%J Transactions of the Association for Computational Linguistics
%D 2021
%V 9
%I MIT Press
%C Cambridge, MA
%F angelidis-etal-2021-extractive
%X We present the Quantized Transformer (QT), an unsupervised system for extractive opinion summarization. QT is inspired by Vector- Quantized Variational Autoencoders, which we repurpose for popularity-driven summarization. It uses a clustering interpretation of the quantized space and a novel extraction algorithm to discover popular opinions among hundreds of reviews, a significant step towards opinion summarization of practical scope. In addition, QT enables controllable summarization without further training, by utilizing properties of the quantized space to extract aspect-specific summaries. We also make publicly available Space, a large-scale evaluation benchmark for opinion summarizers, comprising general and aspect-specific summaries for 50 hotels. Experiments demonstrate the promise of our approach, which is validated by human studies where judges showed clear preference for our method over competitive baselines.
%R 10.1162/tacl_a_00366
%U https://aclanthology.org/2021.tacl-1.17
%U https://doi.org/10.1162/tacl_a_00366
%P 277-293

Markdown (Informal)

[Extractive Opinion Summarization in Quantized Transformer Spaces](https://aclanthology.org/2021.tacl-1.17) (Angelidis et al., TACL 2021)

• Extractive Opinion Summarization in Quantized Transformer Spaces (Angelidis et al., TACL 2021)

ACL

• Stefanos Angelidis, Reinald Kim Amplayo, Yoshihiko Suhara, Xiaolan Wang, and Mirella Lapata. 2021. Extractive Opinion Summarization in Quantized Transformer Spaces. Transactions of the Association for Computational Linguistics, 9:277–293.