=Paper=
{{Paper
|id=Vol-3034/preface
|storemode=property
|title=None
|pdfUrl=https://ceur-ws.org/Vol-3034/preface.pdf
|volume=Vol-3034
}}
==None==
https://ceur-ws.org/Vol-3034/preface.pdf
Proceedings of the 4th Workshop on Deep
Learning for Knowledge Graphs co-located with
International Semantic Web Conference 2021
Mehwish Alam1 , Davide Buscaldi2 , Michael Cochez3 , Francesco Osborne4 ,
Diego Reforgiato Recupero5 , Harald Sack1
1
FIZ Karlsruhe - Leibniz Institute for Information Infrastructure, Germany
2
Laboratoire d’Informatique de Paris Nord, France
3
Vrije Universiteit Amsterdam, the Netherlands
4
Knowledge Media Institute (KMi), The Open University, UK
5
University of Cagliari, Italy
Organizing Committee
– Mehwish Alam, FIZ Karlsruhe - Leibniz Institute for Information Infras-
tructure, Germany
– Davide Buscaldi, Universitè Paris 13, USPC, Paris, France
– Michael Cochez, Vrije University of Amsterdam, the Netherlands
– Francesco Osborne, Knowledge Media Institute (KMi), The Open Uni-
versity, UK
– Diego Reforgiato Recupero, University of Cagliari, Cagliari, Italy
– Harald Sack, FIZ Karlsruhe - Leibniz Institute for Information Infrastruc-
ture, Germany
Program Committee
– Achim Rettinger, Trier University, Germany
– Angelo Salatino, Knowledge Media Institute, Open University, United
Kingdom
– Blerina Gkotse, CERN, Switzerland.
– Danilo Dessı̀, FIZ-Karlsruhe, Karlsruhe Institute of Technology, Germany.
– Femke Ongenae, Ghent University, Belgium.
– Finn Årup Nielsen, Technical University of Denmark, Denmark.
– Genet Asefa Gesese, FIZ-Karlsruhe, Karlsruhe Institute of Technology,
Germany.
– Heiko Paulheim, University of Mannheim, Germany.
– Max Berrendorf, LMU Munich, Germany.
– Mayank Kejriwal, University of Southern California, USA.
– Peter Bloem, Vrije Universiteit Amsterdam, the Netherlands.
– Rima Türker, FIZ-Karlsruhe, Karlsruhe Institute of Technology, Germany.
– Russa Biswas, FIZ-Karlsruhe, Karlsruhe Institute of Technology, Germany.
– Thiviyan Thanapalasingam, University of Amsterdam, the Netherlands.
Preface
Knowledge Graphs have been used in various machine learning tasks by deriving
latent feature representations of entities and relations. Knowledge Graphs rep-
resent formal semantics by describing entities and relationships between them,
and can use ontologies as a schema layer of reference. This way, it is possible to
retrieve implicit knowledge through logical inference rather than only allowing
queries that request explicit knowledge. Deep Learning methods have emerged
from machine learning approaches and became essential for the resolution of
several tasks within the artificial intelligence spectrum. Recently, Deep Learn-
ing methods have been used in conjunction with Knowledge Graphs (i.e., to
represent relationship of the graph in a vector space, to allow companies find
patterns in real-time between interconnected entities, to keep track of invento-
ries of parts further allowing finding materials used in different products, etc.).
Therefore, it has become critical that the Deep Learning and Knowledge Graphs
communities join their forces in order to develop more effective algorithms and
applications. This workshop aimed at reinforcing the relationships between these
communities and intended to be at the center of shared works around topics such
as Deep Learning, Knowledge Graphs, Natural Language Processing, Computa-
tional Linguistics, Big Data, and so on.
Therefore, the goal of this workshop was to provide a meeting forum where
discussions between the relevant stakeholders (researchers from academia, in-
dustry and businessmen) could be stimulated within the Deep Learning and
Knowledge Graphs domains. As the previous edition, this year we noticed a
general attention to our workshop given the more than 10 submissions we re-
ceived and the high number of participants we noticed during the workshop day.
Eight papers have been accepted and discussed within the workshop by authors
from different international institutions. They covered topics such as Knowledge
Graph embeddings, entity summarization, entity type prediction, semantic en-
tity enrichment. We had as invited speaker Prof. Aldo Gangemi who discussed
how knowledge graph embeddings are both an opportunity and a matter of con-
cern for the cognitive scientist, what patterns can be found and what else can
be discovered in the direction of human-centred semantics. We really thank him
for his great talk. We also thank the program committee for their time and work
for reviewing the submitted papers. Although the workshop was held remotely
due to the COVID-19 pandemic, it has been successful by more than 60 partic-
ipants from all around the world. On the workshop website6 it is possible to see
screenshots reflecting some moments of the workshop.
December 2021 Mehwish Alam
Davide Buscaldi
Michael Cochez
Francesco Osborne
Diego Reforgiato Recupero
Harald Sack
6
https://alammehwish.github.io/dl4kg2021/
Contents
Quality Assessment of Knowledge Graph Hierarchies using KG-BERT,
Kinga Szarkowska, Veronique Moore, Pierre-Yves Vandenbussche, Paul Groth
Language Models As or For Knowledge Bases, Simon Razniewski, An-
drew Yates, Nora Kassner, Gerhard Weikum
GraphPOPE: Retaining Structural Graph Information Using Position-
aware Node Embeddings, Jeroen Den Boef, Joran Cornelisse, Paul Groth
Challenges of Applying Knowledge Graph and their Embeddings to a
Real-world Use-case, Rick Petzold, Genet Asefa Gesese, Viktoria Bogdanova,
Thorsten Zylowski, Harald Sack, Mehwish Alam
Knowledge Graph Embeddings or Bias Graph Embeddings? A Study
of Bias in Link Prediction Models, Andrea Rossi, Paolo Merialdo, Do-
natella Firmani
Integrating Contextual Knowledge to Visual Features for Fine Art
Classification, Giovanna Castellano, Giovanni Sansaro, Gennaro Vessio
Generating Table Vector Representations, Aneta Koleva, Martin Ringsquandl,
Mitchell Joblin, Volker Tresp
Understanding Class Representations: An Intrinsic Evaluation of Zero-
Shot Text Classification, Fabian Hoppe, Danilo Dessı̀, Harald Sack