<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peyrard-gurevych-2018-objective">
    <titleInfo>
        <title>Objective Function Learning to Match Human Judgements for Optimization-Based Summarization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maxime</namePart>
        <namePart type="family">Peyrard</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Iryna</namePart>
        <namePart type="family">Gurevych</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marilyn</namePart>
            <namePart type="family">Walker</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Heng</namePart>
            <namePart type="family">Ji</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Amanda</namePart>
            <namePart type="family">Stent</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">New Orleans, Louisiana</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Supervised summarization systems usually rely on supervision at the sentence or n-gram level provided by automatic metrics like ROUGE, which act as noisy proxies for human judgments. In this work, we learn a summary-level scoring function θ including human judgments as supervision and automatically generated data as regularization. We extract summaries with a genetic algorithm using θ as a fitness function. We observe strong and promising performances across datasets in both automatic and manual evaluation.</abstract>
    <identifier type="citekey">peyrard-gurevych-2018-objective</identifier>
    <identifier type="doi">10.18653/v1/N18-2103</identifier>
    <location>
        <url>https://aclanthology.org/N18-2103</url>
    </location>
    <part>
        <date>2018-06</date>
        <extent unit="page">
            <start>654</start>
            <end>660</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Objective Function Learning to Match Human Judgements for Optimization-Based Summarization
%A Peyrard, Maxime
%A Gurevych, Iryna
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F peyrard-gurevych-2018-objective
%X Supervised summarization systems usually rely on supervision at the sentence or n-gram level provided by automatic metrics like ROUGE, which act as noisy proxies for human judgments. In this work, we learn a summary-level scoring function θ including human judgments as supervision and automatically generated data as regularization. We extract summaries with a genetic algorithm using θ as a fitness function. We observe strong and promising performances across datasets in both automatic and manual evaluation.
%R 10.18653/v1/N18-2103
%U https://aclanthology.org/N18-2103
%U https://doi.org/10.18653/v1/N18-2103
%P 654-660

Markdown (Informal)

[Objective Function Learning to Match Human Judgements for Optimization-Based Summarization](https://aclanthology.org/N18-2103) (Peyrard & Gurevych, NAACL 2018)

• Objective Function Learning to Match Human Judgements for Optimization-Based Summarization (Peyrard & Gurevych, NAACL 2018)

ACL

• Maxime Peyrard and Iryna Gurevych. 2018. Objective Function Learning to Match Human Judgements for Optimization-Based Summarization. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 654–660, New Orleans, Louisiana. Association for Computational Linguistics.