%0 Conference Paper %1 liger_om_2020 %A Georgala, Kleanthi %A Sherif, Mohamed Ahmed %A Ngonga Ngomo, Axel-Cyrille %B Proceedings of Ontology Matching Workshop 2020 %D 2020 %K 2020 dice georgala hecate knowgraphs limbo limboproject limes ngonga opal sherif simba %T LIGER -- Link Discovery with Partial Recall %U https://papers.dice-research.org/2020/OM_LIGER/public.pdf %X Modern data-driven frameworks often have to process large amounts of data periodically. Hence, they often operate under time or space constraints. This also holds for Linked Data-driven frameworks when processing RDF data, in particular, when they perform link discovery tasks. In this work, we present a novel approach for link discovery under constraints pertaining to the expected recall of a link discovery task. Given a link specification, the approach aims to find a subsumed link specification that achieves a lower run time than the input specification while abiding by a predefined constraint on the expected recall it has to achieve. Our approach, dubbed LIGER, combines downward refinement oper- ators with monotonicity assumptions to detect such specifications. We evaluate our approach on seven datasets. Our results suggest that the different implemen- tations of LIGER can detect subsumed specifications that abide by expected recall constraints efficiently, thus leading to significantly shorter overall run times than our baseline.

@inproceedings{liger_om_2020, abstract = {Modern data-driven frameworks often have to process large amounts of data periodically. Hence, they often operate under time or space constraints. This also holds for Linked Data-driven frameworks when processing RDF data, in particular, when they perform link discovery tasks. In this work, we present a novel approach for link discovery under constraints pertaining to the expected recall of a link discovery task. Given a link specification, the approach aims to find a subsumed link specification that achieves a lower run time than the input specification while abiding by a predefined constraint on the expected recall it has to achieve. Our approach, dubbed LIGER, combines downward refinement oper- ators with monotonicity assumptions to detect such specifications. We evaluate our approach on seven datasets. Our results suggest that the different implemen- tations of LIGER can detect subsumed specifications that abide by expected recall constraints efficiently, thus leading to significantly shorter overall run times than our baseline.}, added-at = {2021-09-18T10:46:39.000+0200}, author = {Georgala, Kleanthi and Sherif, Mohamed Ahmed and {Ngonga Ngomo}, Axel-Cyrille}, bdsk-url-1 = {https://papers.dice-research.org/2020/OM_LIGER/public.pdf}, biburl = {https://www.bibsonomy.org/bibtex/25169da099f733641699194d39e76af74/dice-research}, booktitle = {Proceedings of Ontology Matching Workshop 2020}, interhash = {5f5fe11860b806ba3cb98c8775c1e51b}, intrahash = {5169da099f733641699194d39e76af74}, keywords = {2020 dice georgala hecate knowgraphs limbo limboproject limes ngonga opal sherif simba}, owner = {sherif}, timestamp = {2023-04-25T16:33:53.000+0200}, title = {{LIGER -- Link Discovery with Partial Recall}}, url = {https://papers.dice-research.org/2020/OM_LIGER/public.pdf}, year = 2020 }