@inproceedings{alsudais-2020-extending,
title = "Extending {I}mage{N}et to {A}rabic using {A}rabic {W}ord{N}et",
author = "Alsudais, Abdulkareem",
editor = "Wang, Xin and
Thomason, Jesse and
Hu, Ronghang and
Chen, Xinlei and
Anderson, Peter and
Wu, Qi and
Celikyilmaz, Asli and
Baldridge, Jason and
Wang, William Yang",
booktitle = "Proceedings of the First Workshop on Advances in Language and Vision Research",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.alvr-1.1/",
doi = "10.18653/v1/2020.alvr-1.1",
pages = "1--6",
abstract = "ImageNet has millions of images that are labeled with English WordNet synsets. This paper investigates the extension of ImageNet to Arabic using Arabic WordNet. The objective is to discover if Arabic synsets can be found for synsets used in ImageNet. The primary finding is the identification of Arabic synsets for 1,219 of the 21,841 synsets used in ImageNet, which represents 1.1 million images. By leveraging the parent-child structure of synsets in ImageNet, this dataset is extended to 10,462 synsets (and 7.1 million images) that have an Arabic label, which is either a match or a direct hypernym, and to 17,438 synsets (and 11 million images) when a hypernym of a hypernym is included. When all hypernyms for a node are considered, an Arabic synset is found for all but four synsets. This represents the major contribution of this work: a dataset of images that have Arabic labels for 99.9{\%} of the images in ImageNet."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alsudais-2020-extending">
<titleInfo>
<title>Extending ImageNet to Arabic using Arabic WordNet</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdulkareem</namePart>
<namePart type="family">Alsudais</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 First Workshop on Advances in Language and Vision Research</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesse</namePart>
<namePart type="family">Thomason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronghang</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinlei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Baldridge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">Yang</namePart>
<namePart type="family">Wang</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>ImageNet has millions of images that are labeled with English WordNet synsets. This paper investigates the extension of ImageNet to Arabic using Arabic WordNet. The objective is to discover if Arabic synsets can be found for synsets used in ImageNet. The primary finding is the identification of Arabic synsets for 1,219 of the 21,841 synsets used in ImageNet, which represents 1.1 million images. By leveraging the parent-child structure of synsets in ImageNet, this dataset is extended to 10,462 synsets (and 7.1 million images) that have an Arabic label, which is either a match or a direct hypernym, and to 17,438 synsets (and 11 million images) when a hypernym of a hypernym is included. When all hypernyms for a node are considered, an Arabic synset is found for all but four synsets. This represents the major contribution of this work: a dataset of images that have Arabic labels for 99.9% of the images in ImageNet.</abstract>
<identifier type="citekey">alsudais-2020-extending</identifier>
<identifier type="doi">10.18653/v1/2020.alvr-1.1</identifier>
<location>
<url>https://aclanthology.org/2020.alvr-1.1/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>1</start>
<end>6</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extending ImageNet to Arabic using Arabic WordNet
%A Alsudais, Abdulkareem
%Y Wang, Xin
%Y Thomason, Jesse
%Y Hu, Ronghang
%Y Chen, Xinlei
%Y Anderson, Peter
%Y Wu, Qi
%Y Celikyilmaz, Asli
%Y Baldridge, Jason
%Y Wang, William Yang
%S Proceedings of the First Workshop on Advances in Language and Vision Research
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F alsudais-2020-extending
%X ImageNet has millions of images that are labeled with English WordNet synsets. This paper investigates the extension of ImageNet to Arabic using Arabic WordNet. The objective is to discover if Arabic synsets can be found for synsets used in ImageNet. The primary finding is the identification of Arabic synsets for 1,219 of the 21,841 synsets used in ImageNet, which represents 1.1 million images. By leveraging the parent-child structure of synsets in ImageNet, this dataset is extended to 10,462 synsets (and 7.1 million images) that have an Arabic label, which is either a match or a direct hypernym, and to 17,438 synsets (and 11 million images) when a hypernym of a hypernym is included. When all hypernyms for a node are considered, an Arabic synset is found for all but four synsets. This represents the major contribution of this work: a dataset of images that have Arabic labels for 99.9% of the images in ImageNet.
%R 10.18653/v1/2020.alvr-1.1
%U https://aclanthology.org/2020.alvr-1.1/
%U https://doi.org/10.18653/v1/2020.alvr-1.1
%P 1-6
Markdown (Informal)
[Extending ImageNet to Arabic using Arabic WordNet](https://aclanthology.org/2020.alvr-1.1/) (Alsudais, ALVR 2020)
ACL