@inproceedings{calabrese-etal-2020-fatality,
title = "Fatality Killed the Cat or: {B}abel{P}ic, a Multimodal Dataset for Non-Concrete Concepts",
author = "Calabrese, Agostina and
Bevilacqua, Michele and
Navigli, Roberto",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.425/",
doi = "10.18653/v1/2020.acl-main.425",
pages = "4680--4686",
abstract = "Thanks to the wealth of high-quality annotated images available in popular repositories such as ImageNet, multimodal language-vision research is in full bloom. However, events, feelings and many other kinds of concepts which can be visually grounded are not well represented in current datasets. Nevertheless, we would expect a wide-coverage language understanding system to be able to classify images depicting recess and remorse, not just cats, dogs and bridges. We fill this gap by presenting BabelPic, a hand-labeled dataset built by cleaning the image-synset association found within the BabelNet Lexical Knowledge Base (LKB). BabelPic explicitly targets non-concrete concepts, thus providing refreshing new data for the community. We also show that pre-trained language-vision systems can be used to further expand the resource by exploiting natural language knowledge available in the LKB. BabelPic is available for download at \url{http://babelpic.org}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="calabrese-etal-2020-fatality">
<titleInfo>
<title>Fatality Killed the Cat or: BabelPic, a Multimodal Dataset for Non-Concrete Concepts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agostina</namePart>
<namePart type="family">Calabrese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Bevilacqua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Thanks to the wealth of high-quality annotated images available in popular repositories such as ImageNet, multimodal language-vision research is in full bloom. However, events, feelings and many other kinds of concepts which can be visually grounded are not well represented in current datasets. Nevertheless, we would expect a wide-coverage language understanding system to be able to classify images depicting recess and remorse, not just cats, dogs and bridges. We fill this gap by presenting BabelPic, a hand-labeled dataset built by cleaning the image-synset association found within the BabelNet Lexical Knowledge Base (LKB). BabelPic explicitly targets non-concrete concepts, thus providing refreshing new data for the community. We also show that pre-trained language-vision systems can be used to further expand the resource by exploiting natural language knowledge available in the LKB. BabelPic is available for download at http://babelpic.org.</abstract>
<identifier type="citekey">calabrese-etal-2020-fatality</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.425</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.425/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>4680</start>
<end>4686</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fatality Killed the Cat or: BabelPic, a Multimodal Dataset for Non-Concrete Concepts
%A Calabrese, Agostina
%A Bevilacqua, Michele
%A Navigli, Roberto
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F calabrese-etal-2020-fatality
%X Thanks to the wealth of high-quality annotated images available in popular repositories such as ImageNet, multimodal language-vision research is in full bloom. However, events, feelings and many other kinds of concepts which can be visually grounded are not well represented in current datasets. Nevertheless, we would expect a wide-coverage language understanding system to be able to classify images depicting recess and remorse, not just cats, dogs and bridges. We fill this gap by presenting BabelPic, a hand-labeled dataset built by cleaning the image-synset association found within the BabelNet Lexical Knowledge Base (LKB). BabelPic explicitly targets non-concrete concepts, thus providing refreshing new data for the community. We also show that pre-trained language-vision systems can be used to further expand the resource by exploiting natural language knowledge available in the LKB. BabelPic is available for download at http://babelpic.org.
%R 10.18653/v1/2020.acl-main.425
%U https://aclanthology.org/2020.acl-main.425/
%U https://doi.org/10.18653/v1/2020.acl-main.425
%P 4680-4686
Markdown (Informal)
[Fatality Killed the Cat or: BabelPic, a Multimodal Dataset for Non-Concrete Concepts](https://aclanthology.org/2020.acl-main.425/) (Calabrese et al., ACL 2020)
ACL