@inproceedings{31806,
  abstract     = {{The creation of an RDF knowledge graph for a particular application commonly involves a pipeline of tools that transform a set ofinput data sources into an RDF knowledge graph in a process called dataset augmentation. The components of such augmentation pipelines often require extensive configuration to lead to satisfactory results. Thus, non-experts are often unable to use them. Wepresent an efficient supervised algorithm based on genetic programming for learning knowledge graph augmentation pipelines of arbitrary length. Our approach uses multi-expression learning to learn augmentation pipelines able to achieve a high F-measure on the training data. Our evaluation suggests that our approach can efficiently learn a larger class of RDF dataset augmentation tasks than the state of the art while using only a single training example. Even on the most complex augmentation problem we posed, our approach consistently achieves an average F1-measure of 99% in under 500 iterations with an average runtime of 16 seconds}},
  author       = {{Dreßler, Kevin and Sherif, Mohamed and Ngonga Ngomo, Axel-Cyrille}},
  booktitle    = {{Proceedings of the 33rd ACM Conference on Hypertext and Hypermedia}},
  keywords     = {{2022 RAKI SFB901 deer dice kevin knowgraphs limes ngonga sherif simba}},
  location     = {{Barcelona (Spain)}},
  title        = {{{ADAGIO - Automated Data Augmentation of Knowledge Graphs Using Multi-expression Learning}}},
  doi          = {{10.1145/3511095.3531287}},
  year         = {{2022}},
}