%0 Generic %1 20142014instance %A Daskalaki, E. %A Fundulaki, I. %A Herschel, M. %A Saveta, T. %D 2014 %E ISWC, %K ldbc-self myown %T Instance Matching Benchmarks for Linked Data %U http://www.ics.forth.gr/isl/BenchmarksTutorial/ %X With the continuously increasing number of datasets published in the Web of Data and form part of the Linked Open Data Cloud, it becomes more and more essential to identify resources that correspond to the same real world object in order to interlink web resources and set the basis for large-scale data integration. This requirement becomes apparent in a multitude of domains ranging from science (marine research, biology, astronomy, pharmacology) to semantic publishing and cultural domains. In this context, instance matching (also referred to as record linkage 16, duplicate detection 3 entity resolution 2, and object identification in the context of databases 18) is of crucial importance. It is though essential at this point to develop, along with instance and entity matching systems, benchmarks to determine the weak and strong points of those systems, as well as their overall quality in order to support users in deciding the system to use for their needs. Hence, well defined, and good quality benchmarks are important for comparing the performance of the developed instance matching systems. In this tutorial we aim at: discussing the state-of-the-art instance matching benchmarks presenting the benchmark design principles providing an analysis of the performance results of instance matching systems for the presented benchmarks presenting the research directions that should be exploited for the creation of novel benchmarks to answer the needs of the Linked Data paradigm.

@misc{20142014instance, abstract = {With the continuously increasing number of datasets published in the Web of Data and form part of the Linked Open Data Cloud, it becomes more and more essential to identify resources that correspond to the same real world object in order to interlink web resources and set the basis for large-scale data integration. This requirement becomes apparent in a multitude of domains ranging from science (marine research, biology, astronomy, pharmacology) to semantic publishing and cultural domains. In this context, instance matching (also referred to as record linkage [16], duplicate detection [3] entity resolution [2], and object identification in the context of databases [18]) is of crucial importance. It is though essential at this point to develop, along with instance and entity matching systems, benchmarks to determine the weak and strong points of those systems, as well as their overall quality in order to support users in deciding the system to use for their needs. Hence, well defined, and good quality benchmarks are important for comparing the performance of the developed instance matching systems. In this tutorial we aim at: discussing the state-of-the-art instance matching benchmarks presenting the benchmark design principles providing an analysis of the performance results of instance matching systems for the presented benchmarks presenting the research directions that should be exploited for the creation of novel benchmarks to answer the needs of the Linked Data paradigm.}, added-at = {2015-04-19T21:03:23.000+0200}, author = {Daskalaki, E. and Fundulaki, I. and Herschel, M. and Saveta, T.}, biburl = {https://www.bibsonomy.org/bibtex/27e723c18b0b7c08d821ad56d81034ba1/fundul}, editor = {ISWC}, howpublished = {ISWC, 2014, Tutorial}, interhash = {2e28b83336a79959c7bab05af46d4975}, intrahash = {7e723c18b0b7c08d821ad56d81034ba1}, keywords = {ldbc-self myown}, month = {October 2014}, timestamp = {2015-04-19T21:03:57.000+0200}, title = {Instance Matching Benchmarks for Linked Data}, url = {http://www.ics.forth.gr/isl/BenchmarksTutorial/}, year = 2014 }