About

Over the past years there has been a rapid growth in the use and the importance of Knowledge Graphs (KGs) along with their application to many important tasks. KGs are large networks of real-world entities described in terms of their semantic types and their relationships to each other. On the other hand, Deep Learning methods have also become an important area of research, achieving some important breakthrough in various research fields, especially Natural Language Processing (NLP) and Image Recognition.

In order to pursue more advanced methodologies, it has become critical that the communities related to Deep Learning, Knowledge Graphs, and NLP join their forces in order to develop more effective algorithms and applications. This workshop, in the wake of other similar efforts at previous Semantic Web conferences such as ESWC2018 as DL4KGs and ISWC2018, aims to reinforce the relationships between these communities and foster inter-disciplinary research in the areas of KG, Deep Learning, and Natural Language Processing.

Keynote Speaker

Volker Tresp

Siemens, Munich, Germany

Title

Abstract

Following Goethe’s proverb, “you only see what you know”, we show how background knowledge formulated as Knowledge Graphs can dramatically improve information extraction from images by deep convolutional networks. We conclude that knowledge graph models, in connection with deep learning, can be the basis for many technical solutions requiring memory and perception, and might be a basis for modern AI.

Short Biography

Volker Tresp is Distinguished Research Scientist at Siemens Corporate Technology and Professor at the Ludwig Maximilian University in Munich. He received his Ph.D. degree from Yale University in 1989 and joined Siemens the same year. At Siemens he has been the head of various research teams in machine learning, data analytics and knowledge representation. He filed more than 70 patent applications, published more than 150 scientific articles, and was inventor of the year of Siemens in 1996. The company Panoratio is a spin-off out of his team. At the Ludwig Maximilian University he teaches an annual course on Machine Learning. His research focus in recent years has been “Machine Learning and Deep Learning with Information Networks” for modelling Knowledge Graphs, medical decision processes, perception, and cognitive memory functions.

Workshop Program and Proceedings

Proceedings are now available on CEUR, click here for accessing.

Accepted Papers.

• Mining Scholarly Data for Fine-Grained Knowledge Graph Construction. Davide Buscaldi, Danilo Dessì, Enrico Motta, Francesco Osborne and Diego Reforgiato Recupero.
• A Comprehensive Survey of Knowledge Graph Embeddings with Literals: Techniques and Applications. Genet Asefa Gesese, Russa Biswas and Harald Sack.
• End-to-End Learning for Answering Structured Queries Directly over Text. Paul Groth, Antony Scerri, Ron Daniel and Bradley Allen.
• Graph-Convolution-Based Classification for Ontology Alignment Change Prediction. Matthias Jurisch and Bodo Igler.
• Loss Functions in Knowledge Graph Embedding Models. Sameh Mohamed, Emir Muñoz, Vit Novacek and Pierre-Yves Vandenbussche.
• Knowledge Reconciliation with Graph Convolutional Networks: Preliminary Results. Pierre Monnin, Chedy Raïssi, Amedeo Napoli and Adrien Coulet.
• Iterative Entity Alignment with Improved Neural Attribute Embedding. Ning Pang, Weixin Zeng, Jiuyang Tang, Zhen Tan and Xiang Zhao.
• Can Knowledge Graphs and Deep Learning Approaches help in Representing, Detecting and Interpreting Metaphors? Mehwish Alam.

Workshop Program.

• Paul Groth, Antony Scerri, Ron Daniel and Bradley Allen. End-to-End Learning for Answering Structured Queries Directly over Text
• Davide Buscaldi, Danilo Dessì, Enrico Motta, Francesco Osborne and Diego Reforgiato Recupero. Mining Scholarly Data for Fine-Grained Knowledge Graph Construction
• Pierre Monnin, Chedy Raïssi, Amedeo Napoli and Adrien Coulet. Knowledge Reconciliation with Graph Convolutional Networks: Preliminary Results

• Matthias Jurisch and Bodo Igler. Graph-Convolution-Based Classification for Ontology Alignment Change Prediction
• Genet Asefa Gesese, Russa Biswas and Harald Sack. A Comprehensive Survey of Knowledge Graph Embeddings with Literals: Techniques and Applications
• Sameh Mohamed, Emir Muñoz, Vit Novacek and Pierre-Yves Vandenbussche. Loss Functions in Knowledge Graph Embedding Models

• Ning Pang, Weixin Zeng, Jiuyang Tang, Zhen Tan and Xiang Zhao. Iterative Entity Alignment with Improved Neural Attribute Embedding
• Mehwish Alam. Can Knowledge Graphs and Deep Learning Approaches help in Representing, Detecting and Interpreting Metaphors?