The book “Embedding Knowledge Graphs with RDF2vec”, co-authored by Heiko Paulheim together with DWS alumni Petar Ristoski and Jan Portisch, has been published at Springer. The book explains the ideas behind one of the most well-known methods for knowledge graph embedding of transformations to ...

We are happy to announce both of our submissions have been accepted for ECML/PKDD 2023 in Turin,Italy (CORE rank A). “Comparing Apples and Oranges? On the Evaluation of Methods for Temporal Knowledge Graph Forecasting” by Julia Gastlinger, Timo Sztyler, Lokesh Sharma, Anett Schülke and Heiner ...

The paper “Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction” by Adrian Kochsiek, Apoorv Saxena, Inderjeet Nair, and Rainer Gemulla has been accepted at the 2023 Repl4NLP Workshop on Representation Learning for NLP, hosted by ACL 2023. Abstract: We propose KGT5-context, a ...

The paper “Simplifying Content-Based Neural News Recommendation: On User Modeling and Training Objectives” by Andreea Iana, Goran Glavaš,  and Heiko Paulheim has been accepted at the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. Abstract: The advent ...

We are happy to announce that the paper “Outlying Aspect Mining via Sum-Product Networks” by Stefan Lüdtke, Christian Bartelt und Heiner Stuckenschmidt has been accepted for the 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) (CORE Rank A, Acceptance Rate 17%).

In courses, all participants are usually provided with identical learning materials, regardless of previous knowledge and ability. As part of the project, a recommendation system is to be developed and tested in two different courses, which provides students with additional materials such as ...

The KISync research project aims to investigate how methods of artificial intelligence (AI) must be applied to solve the decision problems of different processes in the synchronize operational supply chain planning under the influence of uncertainties. Included is primarily intended to support ...

The digitization and optimization of active processes in the construction industry using methods of artificial intelligence is of strategic interest for those involved in construction. The aim of this project application is the development of an AI-based system for the semantic classification and ...

We are happy to announce that the Web Data Commons – Schema.org Table Annotation Benchmark (WDC SOTAB) has won the Dataset Track of the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching (SemTab) at the International Semantic Web Conference 2022.

The German Foundation for Peace Research funds a new project on hate speech analysis on Twitter.