The paper „You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings“ by Daniel Ruffinelli, Samuel Broscheit and Rainer Gemulla has been accepted at the 2020 International Conference of Learning Representations (ICLR).
Knowledge graph embedding (KGE) models learn ...
LibKGE is a PyTorch-based library for efficient training, evaluation, and hyperparameter optimization of knowledge graph embeddings (KGE). It is highly configurable, easy to use, and extensible.
The first DWS PhD Student Poster Session of the FSS2019 DWS Colloquium took place today.
We are very happy to announce that Dr. Han van der Aa will be assigned as Juniorprofessor at the School of Business Informatics and Mathematics in April. Dr. van der Aa reseach focus is data-driven process analytics and he will join the DWS group as 8th professor. Welcome!
The DWS group is happy to announce the new release of the WebDataCommons Microdata, JSON-LD, RDFa and Microformat data corpus. The data has been extracted from the November 2019 version of the Common Crawl covering 2.4 billion HTML pages which originate from 32 million websites (pay-level domains).
On December 5th, Heiko Paulheim has given a keynote speech at the 27th Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2019) in Galway, Ireland, titled „Beyond DBpedia and YAGO - The New Kids on the Knowledge Graph Block“.
The talk introduced two recent knowledge graph ...
Professor Bizer was invited to give the keynote speech at the 9th Joint International Semantic Technology Conference (JIST2019) in Hangzhou, China.
The first version of CaLiGraph, an extensive knowledge graph extracted from categories and list pages in Wikipedia, has been released.
We are happy to announce that Professor Christian Bizer has received the SWSA Ten-Year Award at the 18th International Semantic Web Conference (ISWC2019) in Aukland, New Zealand.
We are happy to announce the release of Version 2.0 of the Web Data Commons Product Data Corpus and Gold Standard for Large-Scale Product Matching. The product data corpus consits of 26 million product offers (16 million English language offers) originating from 79 thousand different e-shops. The ...
Tracking cookies are currently allowed.
Tracking cookies are currently not allowed.