@inbook{46516,
  abstract     = {{Linked knowledge graphs build the backbone of many data-driven applications such as search engines, conversational agents and e-commerce solutions. Declarative link discovery frameworks use complex link specifications to express the conditions under which a link between two resources can be deemed to exist. However, understanding such complex link specifications is a challenging task for non-expert users of link discovery frameworks. In this paper, we address this drawback by devising NMV-LS, a language model-based verbalization approach for translating complex link specifications into natural language. NMV-LS relies on the results of rule-based link specification verbalization to apply continuous training on T5, a large language model based on the Transformerarchitecture. We evaluated NMV-LS on English and German datasets using well-known machine translation metrics such as BLUE, METEOR, ChrF++ and TER. Our results suggest that our approach achieves a verbalization performance close to that of humans and outperforms state of the art approaches. Our source code and datasets are publicly available at https://github.com/dice-group/NMV-LS.}},
  author       = {{Ahmed, Abdullah Fathi Ahmed and Firmansyah, Asep Fajar and Sherif, Mohamed and Moussallem, Diego and Ngonga Ngomo, Axel-Cyrille}},
  booktitle    = {{Natural Language Processing and Information Systems}},
  isbn         = {{9783031353192}},
  issn         = {{0302-9743}},
  publisher    = {{Springer Nature Switzerland}},
  title        = {{{Explainable Integration of Knowledge Graphs Using Large Language Models}}},
  doi          = {{10.1007/978-3-031-35320-8_9}},
  year         = {{2023}},
}

@inproceedings{54616,
  author       = {{Becker, Alexander and Ahmed, Abdullah Fathi Ahmed and Sherif, Mohamed and Ngonga Ngomo, Axel-Cyrille}},
  booktitle    = {{SEMANTiCS}},
  keywords     = {{ahmed becker dice ngonga sail sherif}},
  title        = {{{COBALT: A Content-Based Similarity Approach for Link Discovery over Geospatial Knowledge Graphs}}},
  year         = {{2023}},
}

@inproceedings{46514,
  abstract     = {{Purpose: Data integration and applications across knowledge graphs (KGs) rely heavily on the discovery of links between resources within these KGs. Geospatial link discovery algorithms have to deal with millions of point sets containing billions of points. 
Methodology: To speed up the discovery of geospatial links, we propose COBALT. COBALT combines the content measures with R-tree indexing. The content measures are based on the area, diagonal and distance of the minimum bounding boxes of the polygons which speeds up the process but is not perfectly accurate. We thus propose two polygon splitting approaches for improving the accuracy of COBALT. 
Findings: Our experiments on real-world datasets show that COBALT is able to speed up the topological relation discovery over geospatial KGs by up to 1.47 × 104 times over state-of-the-art linking algorithms while maintaining an F-Measure between 0.7 and 0.9 depending on the relation. Furthermore, we were able to achieve an F-Measure of up to 0.99 by applying our polygon splitting approaches before applying the content measures. 
Value: The process of discovering links between geospatial resources can be significantly faster by sacrificing the optimality of the results. This is especially important for real time data-driven applications such as emergency response, location-based services and traffic management. In future work, additional measures, like the location of polygons or the name of the entity represented by the polygon, could be integrated to further improve the accuracy of the results.}},
  author       = {{Becker, Alexander and Ahmed, Abdullah Fathi Ahmed and Sherif, Mohamed and Ngonga Ngomo, Axel-Cyrille}},
  booktitle    = {{SEMANTiCS}},
  keywords     = {{ahmed becker dice ngonga sail sherif}},
  location     = {{Leipzig, Germany}},
  title        = {{{COBALT: A Content-Based Similarity Approach for Link Discovery over Geospatial Knowledge Graphs}}},
  year         = {{2023}},
}

@misc{45558,
  abstract     = {{Graffiti is an urban phenomenon that is increasingly attracting the interest of the sciences. To the best of our knowledge, no suitable data corpora are available for systematic research until now. The Information System Graffiti in Germany project (Ingrid) closes this gap by dealing with graffiti image collections that have been made available to the project for public use. Within Ingrid, the graffiti images are collected, digitized and annotated. With this work, we aim to support the rapid access to a comprehensive data source on Ingrid targeted especially by researchers. In particular, we present IngridKG, an RDF knowledge graph of annotated graffiti, abides by the Linked Data and FAIR principles. We weekly update IngridKG by augmenting the new annotated graffiti to our knowledge graph. Our generation pipeline applies RDF data conversion, link discovery and data fusion approaches to the original data. The current version of IngridKG contains 460,640,154 triples and is linked to 3 other knowledge graphs by over 200,000 links. In our use case studies, we demonstrate the usefulness of our knowledge graph for different applications.}},
  author       = {{Sherif, Mohamed and Morim da Silva, Ana Alexandra and Pestryakova, Svetlana and Ahmed, Abdullah Fathi Ahmed and Niemann, Sven and Ngonga Ngomo, Axel-Cyrille}},
  publisher    = {{LibreCat University}},
  title        = {{{IngridKG: A FAIR Knowledge Graph of Graffiti}}},
  doi          = {{10.5281/ZENODO.7560242}},
  year         = {{2023}},
}

@inproceedings{29038,
  abstract     = {{An increasing number of heterogeneous datasets abiding by the Linked Data paradigm is published everyday. Discovering links between these datasets is thus central to achieving the vision behind the Data Web. Declarative Link Discovery (LD) frameworks rely on complex Link Specification (LS) to express the conditions under which two resources should be linked. Complex LS combine similarity measures with thresholds to determine whether a given predicate holds between two resources. State of the art LD frameworks rely mostly on string-based similarity measures such as Levenshtein and Jaccard. However, string-based similarity measures often fail to catch the similarity of resources with phonetically similar property values when these property values are represented using different string representation (e.g., names and street labels). In this paper, we evaluate the impact of using phonetics-based similarities in the process of LD. Moreover, we evaluate the impact of phonetic-based similarity measures on a state-of-the-art machine learning approach used to generate LS. Our experiments suggest that the combination of string-based and phonetic-based measures can improve the Fmeasures achieved by LD frameworks on most datasets.}},
  author       = {{Ahmed, Abdullah Fathi Ahmed and Sherif, Mohamed and Ngonga Ngomo, Axel-Cyrille}},
  booktitle    = {{K-CAP 2019: Knowledge Capture Conference}},
  keywords     = {{sys:relevantFor:infai sys:relevantFor:bis sys:relevantFor:ngonga ahmed sherif solide limboproject opal group_aksw dice}},
  title        = {{{Do your Resources Sound Similar? On the Impact of Using Phonetic Similarity in Link Discovery}}},
  year         = {{2019}},
}