<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhaskar-etal-2023-prompted">
    <titleInfo>
        <title>Prompted Opinion Summarization with GPT-3.5</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Adithya</namePart>
        <namePart type="family">Bhaskar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alex</namePart>
        <namePart type="family">Fabbri</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Greg</namePart>
        <namePart type="family">Durrett</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>Large language models have shown impressive performance across a wide variety of tasks, including text summarization. In this paper, we show that this strong performance extends to opinion summarization. We explore several pipeline methods for applying GPT-3.5 to summarize a large collection of user reviews in aprompted fashion. To handle arbitrarily large numbers of user reviews, we explore recursive summarization as well as methods for selecting salient content to summarize through supervised clustering or extraction. On two datasets, an aspect-oriented summarization dataset of hotel reviews (SPACE) and a generic summarization dataset of Amazon and Yelp reviews (FewSum), we show that GPT-3.5 models achieve very strong performance in human evaluation. We argue that standard evaluation metrics do not reflect this, and introduce three new metrics targeting faithfulness, factuality, and genericity to contrast these different methods.</abstract>
    <identifier type="citekey">bhaskar-etal-2023-prompted</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.591</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.591</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>9282</start>
            <end>9300</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Prompted Opinion Summarization with GPT-3.5
%A Bhaskar, Adithya
%A Fabbri, Alex
%A Durrett, Greg
%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 bhaskar-etal-2023-prompted
%X Large language models have shown impressive performance across a wide variety of tasks, including text summarization. In this paper, we show that this strong performance extends to opinion summarization. We explore several pipeline methods for applying GPT-3.5 to summarize a large collection of user reviews in aprompted fashion. To handle arbitrarily large numbers of user reviews, we explore recursive summarization as well as methods for selecting salient content to summarize through supervised clustering or extraction. On two datasets, an aspect-oriented summarization dataset of hotel reviews (SPACE) and a generic summarization dataset of Amazon and Yelp reviews (FewSum), we show that GPT-3.5 models achieve very strong performance in human evaluation. We argue that standard evaluation metrics do not reflect this, and introduce three new metrics targeting faithfulness, factuality, and genericity to contrast these different methods.
%R 10.18653/v1/2023.findings-acl.591
%U https://aclanthology.org/2023.findings-acl.591
%U https://doi.org/10.18653/v1/2023.findings-acl.591
%P 9282-9300

Markdown (Informal)

[Prompted Opinion Summarization with GPT-3.5](https://aclanthology.org/2023.findings-acl.591) (Bhaskar et al., Findings 2023)

• Prompted Opinion Summarization with GPT-3.5 (Bhaskar et al., Findings 2023)

ACL

• Adithya Bhaskar, Alex Fabbri, and Greg Durrett. 2023. Prompted Opinion Summarization with GPT-3.5. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9282–9300, Toronto, Canada. Association for Computational Linguistics.