@inproceedings{davis-etal-2019-deconstructing,
title = "Deconstructing multimodality: visual properties and visual context in human semantic processing",
author = "Davis, Christopher and
Bulat, Luana and
Vero, Anita Lilla and
Shutova, Ekaterina",
editor = "Mihalcea, Rada and
Shutova, Ekaterina and
Ku, Lun-Wei and
Evang, Kilian and
Poria, Soujanya",
booktitle = "Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*{SEM} 2019)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S19-1013",
doi = "10.18653/v1/S19-1013",
pages = "118--124",
abstract = "Multimodal semantic models that extend linguistic representations with additional perceptual input have proved successful in a range of natural language processing (NLP) tasks. Recent research has successfully used neural methods to automatically create visual representations for words. However, these works have extracted visual features from complete images, and have not examined how different kinds of visual information impact performance. In contrast, we construct multimodal models that differentiate between internal visual properties of the objects and their external visual context. We evaluate the models on the task of decoding brain activity associated with the meanings of nouns, demonstrating their advantage over those based on complete images.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="davis-etal-2019-deconstructing">
<titleInfo>
<title>Deconstructing multimodality: visual properties and visual context in human semantic processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Davis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luana</namePart>
<namePart type="family">Bulat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="given">Lilla</namePart>
<namePart type="family">Vero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kilian</namePart>
<namePart type="family">Evang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal semantic models that extend linguistic representations with additional perceptual input have proved successful in a range of natural language processing (NLP) tasks. Recent research has successfully used neural methods to automatically create visual representations for words. However, these works have extracted visual features from complete images, and have not examined how different kinds of visual information impact performance. In contrast, we construct multimodal models that differentiate between internal visual properties of the objects and their external visual context. We evaluate the models on the task of decoding brain activity associated with the meanings of nouns, demonstrating their advantage over those based on complete images.</abstract>
<identifier type="citekey">davis-etal-2019-deconstructing</identifier>
<identifier type="doi">10.18653/v1/S19-1013</identifier>
<location>
<url>https://aclanthology.org/S19-1013</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>118</start>
<end>124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deconstructing multimodality: visual properties and visual context in human semantic processing
%A Davis, Christopher
%A Bulat, Luana
%A Vero, Anita Lilla
%A Shutova, Ekaterina
%Y Mihalcea, Rada
%Y Shutova, Ekaterina
%Y Ku, Lun-Wei
%Y Evang, Kilian
%Y Poria, Soujanya
%S Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F davis-etal-2019-deconstructing
%X Multimodal semantic models that extend linguistic representations with additional perceptual input have proved successful in a range of natural language processing (NLP) tasks. Recent research has successfully used neural methods to automatically create visual representations for words. However, these works have extracted visual features from complete images, and have not examined how different kinds of visual information impact performance. In contrast, we construct multimodal models that differentiate between internal visual properties of the objects and their external visual context. We evaluate the models on the task of decoding brain activity associated with the meanings of nouns, demonstrating their advantage over those based on complete images.
%R 10.18653/v1/S19-1013
%U https://aclanthology.org/S19-1013
%U https://doi.org/10.18653/v1/S19-1013
%P 118-124
Markdown (Informal)
[Deconstructing multimodality: visual properties and visual context in human semantic processing](https://aclanthology.org/S19-1013) (Davis et al., *SEM 2019)
ACL