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.
%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
}