<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-guiding">
    <titleInfo>
        <title>Guiding Abstractive Dialogue Summarization with Content Planning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ye</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaojun</namePart>
        <namePart type="family">Wan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhiping</namePart>
        <namePart type="family">Cai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Abstractive dialogue summarization has recently been receiving more attention. We propose a coarse-to-fine model for generating abstractive dialogue summaries, and introduce a fact-aware reinforcement learning (RL) objective that improves the fact consistency between the dialogue and the generated summary. Initially, the model generates the predicate-argument spans of the dialogue, and then generates the final summary through a fact-aware RL objective. Extensive experiments and analysis on two benchmark datasets demonstrate that our proposed method effectively improves the quality of the generated summary, especially in coherence and consistency.</abstract>
    <identifier type="citekey">wang-etal-2022-guiding</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.248</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.248</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>3408</start>
            <end>3413</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Guiding Abstractive Dialogue Summarization with Content Planning
%A Wang, Ye
%A Wan, Xiaojun
%A Cai, Zhiping
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F wang-etal-2022-guiding
%X Abstractive dialogue summarization has recently been receiving more attention. We propose a coarse-to-fine model for generating abstractive dialogue summaries, and introduce a fact-aware reinforcement learning (RL) objective that improves the fact consistency between the dialogue and the generated summary. Initially, the model generates the predicate-argument spans of the dialogue, and then generates the final summary through a fact-aware RL objective. Extensive experiments and analysis on two benchmark datasets demonstrate that our proposed method effectively improves the quality of the generated summary, especially in coherence and consistency.
%R 10.18653/v1/2022.findings-emnlp.248
%U https://aclanthology.org/2022.findings-emnlp.248
%U https://doi.org/10.18653/v1/2022.findings-emnlp.248
%P 3408-3413

Markdown (Informal)

[Guiding Abstractive Dialogue Summarization with Content Planning](https://aclanthology.org/2022.findings-emnlp.248) (Wang et al., Findings 2022)

• Guiding Abstractive Dialogue Summarization with Content Planning (Wang et al., Findings 2022)

ACL

• Ye Wang, Xiaojun Wan, and Zhiping Cai. 2022. Guiding Abstractive Dialogue Summarization with Content Planning. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3408–3413, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.