Data provenance can support the understanding and debugging of complex data processing pipelines, which are for instance common in data integration scenarios. One task in data integration is entity resolution (ER), i.e., the identification of multiple representations of a same real world entity. This paper focuses of provenance modeling and capture for typical ER tasks. While our definition of ER provenance is independent of the actual language or technology used to define an ER task, the method we implement as a proof of concept instruments ER rules specified in HIL, a high-level data integration language.
%0 Book Section
%1 conf/ipaw/OppoldH18
%A Oppold, Sarah
%A Herschel, Melanie
%B Provenance and Annotation of Data and Processes. IPAW 2018. Lecture Notes in Computer Science
%D 2018
%E Belhajjame, Khalid
%E Gehani, Ashish
%E Alper, Pinar
%I Springer International Publishing
%K from:leonkokkoliadis 2018 sfbtrr161 visus:herschme from:mueller D03 visus
%P 226-230
%R 10.1007/978-3-319-98379-0_25
%T Provenance for Entity Resolution
%U https://doi.org/10.1007/978-3-319-98379-0_25
%V 11017
%X Data provenance can support the understanding and debugging of complex data processing pipelines, which are for instance common in data integration scenarios. One task in data integration is entity resolution (ER), i.e., the identification of multiple representations of a same real world entity. This paper focuses of provenance modeling and capture for typical ER tasks. While our definition of ER provenance is independent of the actual language or technology used to define an ER task, the method we implement as a proof of concept instruments ER rules specified in HIL, a high-level data integration language.
%@ 978-3-319-98379-0
@inbook{conf/ipaw/OppoldH18,
abstract = {Data provenance can support the understanding and debugging of complex data processing pipelines, which are for instance common in data integration scenarios. One task in data integration is entity resolution (ER), i.e., the identification of multiple representations of a same real world entity. This paper focuses of provenance modeling and capture for typical ER tasks. While our definition of ER provenance is independent of the actual language or technology used to define an ER task, the method we implement as a proof of concept instruments ER rules specified in HIL, a high-level data integration language.},
added-at = {2020-10-09T12:31:47.000+0200},
author = {Oppold, Sarah and Herschel, Melanie},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2f93071b77f2f182f55ea179a8b7c6c20/visus},
booktitle = { Provenance and Annotation of Data and Processes. IPAW 2018. Lecture Notes in Computer Science},
description = {Provenance for Entity Resolution},
doi = {10.1007/978-3-319-98379-0_25},
editor = {Belhajjame, Khalid and Gehani, Ashish and Alper, Pinar},
ee = {https://doi.org/10.1007/978-3-319-98379-0_25},
interhash = {59cba763b08dc22a8630dc2aed9bd709},
intrahash = {f93071b77f2f182f55ea179a8b7c6c20},
isbn = {978-3-319-98379-0},
keywords = {from:leonkokkoliadis 2018 sfbtrr161 visus:herschme from:mueller D03 visus},
pages = {226-230},
publisher = {Springer International Publishing},
timestamp = {2020-10-09T10:31:47.000+0200},
title = {Provenance for Entity Resolution},
url = {https://doi.org/10.1007/978-3-319-98379-0_25},
volume = 11017,
year = 2018
}