<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hill-etal-2014-multi">
    <titleInfo>
        <title>Multi-Modal Models for Concrete and Abstract Concept Meaning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Felix</namePart>
        <namePart type="family">Hill</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Roi</namePart>
        <namePart type="family">Reichart</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anna</namePart>
        <namePart type="family">Korhonen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2014</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Multi-modal models that learn semantic representations from both linguistic and perceptual input outperform language-only models on a range of evaluations, and better reflect human concept acquisition. Most perceptual input to such models corresponds to concrete noun concepts and the superiority of the multi-modal approach has only been established when evaluating on such concepts. We therefore investigate which concepts can be effectively learned by multi-modal models. We show that concreteness determines both which linguistic features are most informative and the impact of perceptual input in such models. We then introduce ridge regression as a means of propagating perceptual information from concrete nouns to more abstract concepts that is more robust than previous approaches. Finally, we present weighted gram matrix combination, a means of combining representations from distinct modalities that outperforms alternatives when both modalities are sufficiently rich.</abstract>
    <identifier type="citekey">hill-etal-2014-multi</identifier>
    <identifier type="doi">10.1162/tacl_a_00183</identifier>
    <location>
        <url>https://aclanthology.org/Q14-1023</url>
    </location>
    <part>
        <date>2014</date>
        <detail type="volume"><number>2</number></detail>
        <extent unit="page">
            <start>285</start>
            <end>296</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Multi-Modal Models for Concrete and Abstract Concept Meaning
%A Hill, Felix
%A Reichart, Roi
%A Korhonen, Anna
%J Transactions of the Association for Computational Linguistics
%D 2014
%V 2
%I MIT Press
%C Cambridge, MA
%F hill-etal-2014-multi
%X Multi-modal models that learn semantic representations from both linguistic and perceptual input outperform language-only models on a range of evaluations, and better reflect human concept acquisition. Most perceptual input to such models corresponds to concrete noun concepts and the superiority of the multi-modal approach has only been established when evaluating on such concepts. We therefore investigate which concepts can be effectively learned by multi-modal models. We show that concreteness determines both which linguistic features are most informative and the impact of perceptual input in such models. We then introduce ridge regression as a means of propagating perceptual information from concrete nouns to more abstract concepts that is more robust than previous approaches. Finally, we present weighted gram matrix combination, a means of combining representations from distinct modalities that outperforms alternatives when both modalities are sufficiently rich.
%R 10.1162/tacl_a_00183
%U https://aclanthology.org/Q14-1023
%U https://doi.org/10.1162/tacl_a_00183
%P 285-296

Markdown (Informal)

[Multi-Modal Models for Concrete and Abstract Concept Meaning](https://aclanthology.org/Q14-1023) (Hill et al., TACL 2014)

• Multi-Modal Models for Concrete and Abstract Concept Meaning (Hill et al., TACL 2014)

ACL

• Felix Hill, Roi Reichart, and Anna Korhonen. 2014. Multi-Modal Models for Concrete and Abstract Concept Meaning. Transactions of the Association for Computational Linguistics, 2:285–296.