<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gelderloos-chrupala-2016-phonemes">
    <titleInfo>
        <title>From phonemes to images: levels of representation in a recurrent neural model of visually-grounded language learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lieke</namePart>
        <namePart type="family">Gelderloos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Grzegorz</namePart>
        <namePart type="family">Chrupała</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2016-dec</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
        </titleInfo>
        <originInfo>
            <publisher>The COLING 2016 Organizing Committee</publisher>
            <place>
                <placeTerm type="text">Osaka, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present a model of visually-grounded language learning based on stacked gated recurrent neural networks which learns to predict visual features given an image description in the form of a sequence of phonemes. The learning task resembles that faced by human language learners who need to discover both structure and meaning from noisy and ambiguous data across modalities. We show that our model indeed learns to predict features of the visual context given phonetically transcribed image descriptions, and show that it represents linguistic information in a hierarchy of levels: lower layers in the stack are comparatively more sensitive to form, whereas higher layers are more sensitive to meaning.</abstract>
    <identifier type="citekey">gelderloos-chrupala-2016-phonemes</identifier>
    <location>
        <url>https://aclanthology.org/C16-1124</url>
    </location>
    <part>
        <date>2016-dec</date>
        <extent unit="page">
            <start>1309</start>
            <end>1319</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T From phonemes to images: levels of representation in a recurrent neural model of visually-grounded language learning
%A Gelderloos, Lieke
%A Chrupała, Grzegorz
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 dec
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F gelderloos-chrupala-2016-phonemes
%X We present a model of visually-grounded language learning based on stacked gated recurrent neural networks which learns to predict visual features given an image description in the form of a sequence of phonemes. The learning task resembles that faced by human language learners who need to discover both structure and meaning from noisy and ambiguous data across modalities. We show that our model indeed learns to predict features of the visual context given phonetically transcribed image descriptions, and show that it represents linguistic information in a hierarchy of levels: lower layers in the stack are comparatively more sensitive to form, whereas higher layers are more sensitive to meaning.
%U https://aclanthology.org/C16-1124
%P 1309-1319

Markdown (Informal)

[From phonemes to images: levels of representation in a recurrent neural model of visually-grounded language learning](https://aclanthology.org/C16-1124) (Gelderloos & Chrupała, COLING 2016)

• From phonemes to images: levels of representation in a recurrent neural model of visually-grounded language learning (Gelderloos & Chrupała, COLING 2016)

ACL

• Lieke Gelderloos and Grzegorz Chrupała. 2016. From phonemes to images: levels of representation in a recurrent neural model of visually-grounded language learning. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1309–1319, Osaka, Japan. The COLING 2016 Organizing Committee.