@inproceedings{bielefeld-etal-2024-wiki,
title = "{W}iki-{VEL}: Visual Entity Linking for Structured Data on Wikimedia Commons",
author = {Bielefeld, Philipp and
Geppert, Jasmin and
G{\"u}ven, Necdet and
John, Melna and
Ziupka, Adrian and
Kaffee, Lucie-Aim{\'e}e and
Biswas, Russa and
De Melo, Gerard},
editor = "Gu, Jing and
Fu, Tsu-Jui (Ray) and
Hudson, Drew and
Celikyilmaz, Asli and
Wang, William",
booktitle = "Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.alvr-1.16/",
doi = "10.18653/v1/2024.alvr-1.16",
pages = "186--194",
abstract = "Describing Wikimedia Commons images using Wikidata{'}s structured data enables a wide range of automation tasks, such as search and organization, as well as downstream tasks, such as labeling images or training machine learning models. However, there is currently a lack of structured data-labelled images on Wikimedia Commons.To close this gap, we propose the task of \textit{Visual Entity Linking (VEL) for Wikimedia Commons}, in which we create new labels for Wikimedia Commons images from Wikidata items. VEL is a crucial tool for improving information retrieval, search, content understanding, cross-modal applications, and various machine-learning tasks. In this paper, we propose a method to create new labels for Wikimedia Commons images from Wikidata items. To this end, we create a novel dataset leveraging community-created structured data on Wikimedia Commons and fine-tuning pre-trained models based on the CLIP architecture. Although the best-performing models show promising results, the study also identifies key challenges of the data and the task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bielefeld-etal-2024-wiki">
<titleInfo>
<title>Wiki-VEL: Visual Entity Linking for Structured Data on Wikimedia Commons</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Bielefeld</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jasmin</namePart>
<namePart type="family">Geppert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Necdet</namePart>
<namePart type="family">Güven</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melna</namePart>
<namePart type="family">John</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="family">Ziupka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucie-Aimée</namePart>
<namePart type="family">Kaffee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Russa</namePart>
<namePart type="family">Biswas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerard</namePart>
<namePart type="family">De Melo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsu-Jui</namePart>
<namePart type="given">(Ray)</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Drew</namePart>
<namePart type="family">Hudson</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">William</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">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Describing Wikimedia Commons images using Wikidata’s structured data enables a wide range of automation tasks, such as search and organization, as well as downstream tasks, such as labeling images or training machine learning models. However, there is currently a lack of structured data-labelled images on Wikimedia Commons.To close this gap, we propose the task of Visual Entity Linking (VEL) for Wikimedia Commons, in which we create new labels for Wikimedia Commons images from Wikidata items. VEL is a crucial tool for improving information retrieval, search, content understanding, cross-modal applications, and various machine-learning tasks. In this paper, we propose a method to create new labels for Wikimedia Commons images from Wikidata items. To this end, we create a novel dataset leveraging community-created structured data on Wikimedia Commons and fine-tuning pre-trained models based on the CLIP architecture. Although the best-performing models show promising results, the study also identifies key challenges of the data and the task.</abstract>
<identifier type="citekey">bielefeld-etal-2024-wiki</identifier>
<identifier type="doi">10.18653/v1/2024.alvr-1.16</identifier>
<location>
<url>https://aclanthology.org/2024.alvr-1.16/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>186</start>
<end>194</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Wiki-VEL: Visual Entity Linking for Structured Data on Wikimedia Commons
%A Bielefeld, Philipp
%A Geppert, Jasmin
%A Güven, Necdet
%A John, Melna
%A Ziupka, Adrian
%A Kaffee, Lucie-Aimée
%A Biswas, Russa
%A De Melo, Gerard
%Y Gu, Jing
%Y Fu, Tsu-Jui (Ray)
%Y Hudson, Drew
%Y Celikyilmaz, Asli
%Y Wang, William
%S Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F bielefeld-etal-2024-wiki
%X Describing Wikimedia Commons images using Wikidata’s structured data enables a wide range of automation tasks, such as search and organization, as well as downstream tasks, such as labeling images or training machine learning models. However, there is currently a lack of structured data-labelled images on Wikimedia Commons.To close this gap, we propose the task of Visual Entity Linking (VEL) for Wikimedia Commons, in which we create new labels for Wikimedia Commons images from Wikidata items. VEL is a crucial tool for improving information retrieval, search, content understanding, cross-modal applications, and various machine-learning tasks. In this paper, we propose a method to create new labels for Wikimedia Commons images from Wikidata items. To this end, we create a novel dataset leveraging community-created structured data on Wikimedia Commons and fine-tuning pre-trained models based on the CLIP architecture. Although the best-performing models show promising results, the study also identifies key challenges of the data and the task.
%R 10.18653/v1/2024.alvr-1.16
%U https://aclanthology.org/2024.alvr-1.16/
%U https://doi.org/10.18653/v1/2024.alvr-1.16
%P 186-194
Markdown (Informal)
[Wiki-VEL: Visual Entity Linking for Structured Data on Wikimedia Commons](https://aclanthology.org/2024.alvr-1.16/) (Bielefeld et al., ALVR 2024)
ACL
- Philipp Bielefeld, Jasmin Geppert, Necdet Güven, Melna John, Adrian Ziupka, Lucie-Aimée Kaffee, Russa Biswas, and Gerard De Melo. 2024. Wiki-VEL: Visual Entity Linking for Structured Data on Wikimedia Commons. In Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR), pages 186–194, Bangkok, Thailand. Association for Computational Linguistics.