<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cai-etal-2017-pay">
    <titleInfo>
        <title>Pay Attention to the Ending:Strong Neural Baselines for the ROC Story Cloze Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zheng</namePart>
        <namePart type="family">Cai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lifu</namePart>
        <namePart type="family">Tu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kevin</namePart>
        <namePart type="family">Gimpel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Regina</namePart>
            <namePart type="family">Barzilay</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Min-Yen</namePart>
            <namePart type="family">Kan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vancouver, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We consider the ROC story cloze task (Mostafazadeh et al., 2016) and present several findings. We develop a model that uses hierarchical recurrent networks with attention to encode the sentences in the story and score candidate endings. By discarding the large training set and only training on the validation set, we achieve an accuracy of 74.7%. Even when we discard the story plots (sentences before the ending) and only train to choose the better of two endings, we can still reach 72.5%. We then analyze this “ending-only” task setting. We estimate human accuracy to be 78% and find several types of clues that lead to this high accuracy, including those related to sentiment, negation, and general ending likelihood regardless of the story context.</abstract>
    <identifier type="citekey">cai-etal-2017-pay</identifier>
    <identifier type="doi">10.18653/v1/P17-2097</identifier>
    <location>
        <url>https://aclanthology.org/P17-2097</url>
    </location>
    <part>
        <date>2017-07</date>
        <extent unit="page">
            <start>616</start>
            <end>622</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Pay Attention to the Ending:Strong Neural Baselines for the ROC Story Cloze Task
%A Cai, Zheng
%A Tu, Lifu
%A Gimpel, Kevin
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F cai-etal-2017-pay
%X We consider the ROC story cloze task (Mostafazadeh et al., 2016) and present several findings. We develop a model that uses hierarchical recurrent networks with attention to encode the sentences in the story and score candidate endings. By discarding the large training set and only training on the validation set, we achieve an accuracy of 74.7%. Even when we discard the story plots (sentences before the ending) and only train to choose the better of two endings, we can still reach 72.5%. We then analyze this “ending-only” task setting. We estimate human accuracy to be 78% and find several types of clues that lead to this high accuracy, including those related to sentiment, negation, and general ending likelihood regardless of the story context.
%R 10.18653/v1/P17-2097
%U https://aclanthology.org/P17-2097
%U https://doi.org/10.18653/v1/P17-2097
%P 616-622

Markdown (Informal)

[Pay Attention to the Ending:Strong Neural Baselines for the ROC Story Cloze Task](https://aclanthology.org/P17-2097) (Cai et al., ACL 2017)

• Pay Attention to the Ending:Strong Neural Baselines for the ROC Story Cloze Task (Cai et al., ACL 2017)

ACL

• Zheng Cai, Lifu Tu, and Kevin Gimpel. 2017. Pay Attention to the Ending:Strong Neural Baselines for the ROC Story Cloze Task. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 616–622, Vancouver, Canada. Association for Computational Linguistics.