Lecture Notes in Computer Science
Volume 1 / 1973 to Volume 14956 / 2024
Book Series
Volume 1 / 1973 to Volume 14956 / 2024
Book and Conference Proceedings
21st International Conference, ESWC 2024, Hersonissos, Crete, Greece, May 26–30, 2024, Proceedings, Part I
Chapter and Conference Paper
Knowledge graph embedding models (KGEMs) developed for link prediction learn vector representations for entities in a knowledge graph, known as embeddings. A common tacit assumption is the KGE entity similarity a...
Book and Conference Proceedings
21st International Conference, ESWC 2024, Hersonissos, Crete, Greece, May 26–30, 2024, Proceedings, Part II
Book Series
Chapter
Word embedding techniques have been developed to assign words to vectors in a vector space. One of the earliest such methods was word2vec, published in 2013 – and embeddings have gathered a tremendous uptake i...
Chapter
In this chapter, we highlight a few shortcomings of RDF2vec, and we discuss possible future ways to mitigate those. Among the most prominent ones, there are the handling of literal values (which are currently ...
Chapter and Conference Paper
Knowledge graphs and graph databases are nowadays extensively used in various domains. However, manually creating knowledge graphs using existing ontology concepts presents significant challenges. On the other...
Chapter and Conference Paper
Knowledge Graphs (KGs) are a powerful tool for representing domain knowledge in a way that is interpretable for both humans and machines. They have emerged as enablers of semantic integration in various domain...
Chapter and Conference Paper
Many machine learning (ML) libraries are accessible online for ML practitioners. Typical ML pipelines are complex and consist of a series of steps, each of them invoking several ML libraries. In this demo pape...
Chapter
In this chapter, the basic concept of a knowledge graph is introduced. We discuss why knowledge graphs are important for machine learning and data mining tasks, and we show classic feature extraction or propos...
Chapter
RDF2vec (and other techniques) provide embedding vectors for knowledge graphs. While we have used a simple node classification task so far, this chapter introduces a few datasets and three common benchmarks fo...
Chapter
On larger knowledge graphs, RDF2vec models can be very expensive to train. In this chapter, we look at two techniques that make RDF2vec easier to use with large knowledge graphs. First, we look at a knowledge ...
Chapter and Conference Paper
More and more knowledge graphs (KGs) are generated in various domains. Applications using more than one KG require an integrated view of those KGs, which, in the first place, requires a common schema or ontolo...
Chapter and Conference Paper
Entity Linking (EL) is the task of detecting mentions of entities in text and disambiguating them to a reference knowledge base. Most prevalent EL approaches assume that the reference knowledge base is complet...
Chapter and Conference Paper
A knowledge graph is a powerful representation of real-world entities and their relations. The vast majority of these relations are defined as positive statements, but the importance of negative statements is ...
Chapter
Depending on the problem at hand, one might think of different tweaks to the RDF2vec algorithm, many of which have been discussed in the past. Those tweaks encompass various steps of the pipeline: reasoners ha...
Chapter
In recent years, a long list of research works has been published which utilize knowledge graph embeddings for link prediction (rather than node classification, which we have considered so far). In this chapte...
Book
Chapter and Conference Paper
The overall AI trend of creating neuro-symbolic systems is reflected in the Semantic Web community with an increased interest in the development of systems that rely on both Semantic Web resources and Machine Lea...