=Paper=
{{Paper
|id=Vol-3342/preface
|storemode=property
|title=None
|pdfUrl=https://ceur-ws.org/Vol-3342/preface.pdf
|volume=Vol-3342
}}
==None==
https://ceur-ws.org/Vol-3342/preface.pdf
Proceedings of the 5th Workshop on Deep
Learning for Knowledge Graphs co-located with
International Semantic Web Conference 2022
Mehwish Alam1 , Davide Buscaldi2 , Michael Cochez3 , Francesco Osborne4 ,
Diego Reforgiato Recupero5
1
FIZ-Karlsruhe, Leibniz Institute for Information Infrastrcuture, 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, Télécom Paris, Institut Polytechnique de Paris, France
– 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
Program Committee
– Genet Asefa Gesese, FIZ Karlsruhe & KIT Karlsruhe
– Longquan Jiang, University Hamburg
– Danilo Dessı̀, University of Cagliari
– Yiyi Chen, University of Aalborg
– Andreea Iana, University of Mannheim
– Mehdi Ali, University of Bonn
– Daniel Daza, Vrije Universiteit Amsterdam
– Daniele Dell’Aglio, Aalborg University
– Pierre Monnin, Orange, Belfort, France
– Russa Biswas, FIZ Karlsruhe & KIT Karlsruhe
– Paul Groth, University of Amsterdam
– Angelo Salatino, The Open University
– Simone Angioni, University of Cagliari
– Rima Türker, FIZ-Karlsruhe
– Xi Yan, Hamburg University
– Heiko Paulheim, University of Mannheim
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 that more than 11 submissions we re-
ceived and the high number of participants we noticed during the workshop day.
Ten papers have been accepted and discussed within the workshop by authors
from different international institutions. They covered topics such as question
answering, temporal Knowledge Graph embeddings, transformer-based entity
detection, language model detection, link prediction, sparsity in cultural her-
itage image archives, multi-label classification. We had as invited speaker Prof.
Afshin Sadeghi who discussed how to embed a type of dynamic KGs that con-
stantly grow by integrating a stream of new facts. These ever-growing graphs
are known as Accrescent knowledge Graphs (AKG). In contrast to discrete-time
dynamic graphs that different snapshots of a KG are considered, the training
of AKGs involves training upon the stream of new triples. 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 and attended by more than 60 participants from all around
the world. On the workshop website6 it is possible to see screenshots reflecting
some moments of the workshop.
December 2022 Mehwish Alam, Davide Buscaldi, Michael Cochez,
Francesco Osborne, and Diego Reforgiato Recupero
6
https://alammehwish.github.io/dl4kg2022/
Contents
Towards A Question Answering System over Temporal Knowledge
Graph Embedding Kristian Otte, Kristian Simoni Vestermark, KHuan
Li and Daniele Dell’Aglio
Transformer-based Subject Entity Detection in Wikipedia Listings,
Nicolas Heist and Heiko Paulheim
Improving Language Model Predictions via Prompts Enriched with
Knowledge Graphs, Ryan Brate, Minh-Hoang Dang, Fabian Hoppe, Yuan
He, Albert Meroño-Peñuela and Vijay Sadashivaiah
Knowledge Graph Embeddings for Link Prediction: Beware of Se-
mantics!, Nicolas Hubert, Pierre Monnin, Armelle Brun and Davy Monticolo
Neuro-symbolic learning for dealing with sparsity in cultural heritage
image archives: an empirical journey, Agnese Chiatti and Enrico Daga
Bilingual Question Answering over DBpedia Abstracts through Ma-
chine Translation and BERT Michalis Mountantonakis,, Michalis Bas-
takis, Loukas Mertzanis and Yannis Tzitzikas
A Closer Look at Sum-based Embeddings for Knowledge Graphs Con-
taining Procedural Knowledge, Richard Nordsieck, Michael Heider, Anton
Hummel and Joerg Haehner
Knowledge Graph Embeddings for Causal Relation Prediction, Aamod
Khatiwada, Sola Shirai, Kavitha Srinivas and Oktie Hassanzadeh
Multi-label Classification using BERT and Knowledge Graphs with
a Limited Training Dataset, Malick Ebiele, Lucy McKenna, Malika Ben-
dechache and Rob Brennan
CosmOntology: Creating an Ontology of the Cosmos, Vasilis Efthymiou