Home 9 News 9 Awarded: DSIS research group of Lamarr PI Prof. Dr. Demidova receives multiple awards at ISWC 2023

Awarded: DSIS research group of Lamarr PI Prof. Dr. Demidova receives multiple awards at ISWC 2023

Please contact us for further information.

The Data Science and Intelligent Systems (DSIS) research group, led by Lamarr’s Principal Investigator Prof. Dr. Elena Demidova at the University of Bonn and the Lamarr Institute, has accomplished a remarkable achievement at the 22nd International Semantic Web Conference (ISWC 2023). Two DSIS research papers won the conference’s most prestigious paper awards.

The Best Research Track Paper Award was given to the paper “Spatial Link Prediction with Spatial and Semantic Embeddings” by Genivika Mann, Alishiba Dsouza, Ran Yu, and Elena Demidova. 

This work addresses a critical limitation of geographic knowledge graphs – the lack of semantic relations between geographic entities due to their flat structure. The authors tackle the challenge by two novel approaches for predicting spatial links in sparsely interlinked knowledge graphs: supervised spatial link prediction and unsupervised inductive spatial link prediction. These approaches leverage the wealth of literal values in geographic knowledge graphs through spatial and semantic embeddings. The evaluation was conducted on the WorldKG knowledge graph developed by the DSIS research group – a comprehensive large-scale geospatial knowledge graph that provides a semantic representation of geographic entities from over 188 countries. Read the full paper here

The Best Research Track Student Paper Award was given to the paper “Iterative Geographic Entity Alignment with Cross-Attention” by Alishiba Dsouza, Ran Yu, Moritz Windoffer, and Elena Demidova.

This paper introduces IGEA, a novel cross-attention-based iterative alignment approach tackling challenges in aligning schemas and entities of community-created geographic data. IGEA overcomes differences in entity representations, sparse interlinking, and high schema heterogeneity. Experiments on real-world datasets from various countries demonstrated that IGEA improves entity alignment performance by up to 18% points in the F1 score compared to the state-of-the-art baseline methods. The iterative method also enhances the performance of entity and tag-to-class alignment by 7 and 8% points in F1-score, respectively.  Read the full paper here.

We hope that novel algorithms and research results presented in these publications and the openly available WorldKG knowledge graph released by the DSIS research group will inspire new research avenues in semantic spatio-temporal data analytics.

Further Information

About the DSIS Research Group

The Data Science & Intelligent Systems (DSIS) Research Group, led by Prof. Dr. Elena Demidova at the University of Bonn and the Lamarr Institute for Machine Learning and Artificial Intelligence, develops innovative machine-learning- and knowledge-based, interactive, transparent, and explainable data science methods for large-scale, heterogeneous data sets. DSIS research interests include spatio-temporal and multilingual data, Open Data, the Web, and Semantic Web.  Application areas include mobility, smart cities, supply chains, and healthcare. For more information, please visit the homepage.  

About The ISWC 2023

The 22nd International Semantic Web Conference (ISWC 2023) is the premier international forum for the Semantic Web community. The ISWC 2023 brings together researchers, practitioners, and industry specialists to discuss, advance, and shape the future of semantic technologies.  For more information, please visit the conference website.

Acknowledgements

The work on these publications was partially funded by the DFG, German Research Foundation (“WorldKG”, 424985896), the Federal Ministry for Economic Affairs and Climate Action (BMWK), Germany (“ATTENTION!”, 01MJ22012C), and DAAD/BMBF, Germany (“KOALA”, 57600865).