Universität Bonn

Data Science & Intelligent Systems


Best Paper Award ISWC 2023
© 2023 DSIS

The Best Research Track Paper Award at The 22nd International Semantic Web Conference (ISWC) 2023, Athens, Greece 

Genivika Mann, Alishiba Dsouza, Ran Yu, Elena Demidova.
Spatial Link Prediction with Spatial and Semantic Embeddings.
ISWC 2023. Springer. BEST PAPER AWARD (Research Track). [URL]

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. 

Best Student Paper Award ISWC 2023.png
© 2023 DSIS

The Best Research Track Student Paper Award at The 22nd International Semantic Web Conference (ISWC) 2023, Athens, Greece

Alishiba Dsouza, Ran Yu, Moritz Windoffer, Elena Demidova.
Iterative Geographic Entity Alignment with Cross-Attention.
ISWC 2023. Springer. BEST STUDENT PAPER AWARD (Research Track). [URL]

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 significantly 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.  

Award Daria Gurtovoy
© 2022 University of Bonn

Grace-Hopper-Award for Daria Gurtovoy
Daria Gurtovoy received the Grace-Hopper-Award for her Bachelor thesis “Linking Street Names in OpenStreetMap to Persons in Knowledge Graphs” from the Computer Science Institute of the University of Bonn.

In her bachelor thesis entitled “Linking Street Names in OpenStreetMap to Persons in Knowledge Graphs”, written in collaboration with the Data Science and Intelligent Systems research group (DSIS) in the context of the DFG-funded project “WorldKG”, Daria has developed a novel approach for interlinking streets in OpenStreetMap and persons giving names to these streets in the Wikidata knowledge graph.

Her approach achieved significant improvements compared to the baselines and established over 180,000 links for the streets in Germany. The linking approach developed in her bachelor thesis was presented as a poster at the ACM Web Conference 2022

We congratulate Daria and wish her all the best for her future studies and research.

Wird geladen