The approach of using ontology reasoning to cleanse the output of information extraction tools was first articulated in SemantiClean. A limiting factor in applying this approach has been that ontology reasoning to find inconsistencies does not scale to the size of data produced by information extraction tools. In this paper, we describe techniques to scale inconsistency detection, and illustrate the use of our techniques to produce a consistent subset of a knowledge base with several thousand inconsistencies.
%0 Conference Paper
%1 Dolby/2007/Scalable
%A Dolby, Julian
%A Fan, James
%A Fokoue, Achille
%A Kalyanpur, Aditya
%A Kershenbaum, Aaron
%A Ma, Li
%A Murdock, William
%A Srinivas, Kavitha
%A Welty, Christopher
%B Proceedings of the 6th International Semantic Web Conference and 2nd Asian Semantic Web Conference (ISWC/ASWC2007), Busan, South Korea
%C Berlin, Heidelberg
%D 2007
%E Aberer, Karl
%E Choi, Key-Sun
%E Noy, Natasha
%E Allemang, Dean
%E Lee, Kyung-Il
%E Nixon, Lyndon J B
%E Golbeck, Jennifer
%E Mika, Peter
%E Maynard, Diana
%E Schreiber, Guus
%E Cudré-Mauroux, Philippe
%I Springer Verlag
%K 2007 application_software cleanup datum extraction information iswc ontology research_02 scalable semantic_web using
%P 99-112
%T Scalable Cleanup of Information Extraction Data Using Ontologies
%U http://iswc2007.semanticweb.org/papers/99.pdf
%V 4825
%X The approach of using ontology reasoning to cleanse the output of information extraction tools was first articulated in SemantiClean. A limiting factor in applying this approach has been that ontology reasoning to find inconsistencies does not scale to the size of data produced by information extraction tools. In this paper, we describe techniques to scale inconsistency detection, and illustrate the use of our techniques to produce a consistent subset of a knowledge base with several thousand inconsistencies.
@inproceedings{Dolby/2007/Scalable,
abstract = {The approach of using ontology reasoning to cleanse the output of information extraction tools was first articulated in SemantiClean. A limiting factor in applying this approach has been that ontology reasoning to find inconsistencies does not scale to the size of data produced by information extraction tools. In this paper, we describe techniques to scale inconsistency detection, and illustrate the use of our techniques to produce a consistent subset of a knowledge base with several thousand inconsistencies.},
added-at = {2007-11-07T19:13:58.000+0100},
address = {Berlin, Heidelberg},
author = {Dolby, Julian and Fan, James and Fokoue, Achille and Kalyanpur, Aditya and Kershenbaum, Aaron and Ma, Li and Murdock, William and Srinivas, Kavitha and Welty, Christopher},
biburl = {https://www.bibsonomy.org/bibtex/2b75014c7cf2e004bc739d0210731389e/iswc2007},
booktitle = {Proceedings of the 6th International Semantic Web Conference and 2nd Asian Semantic Web Conference (ISWC/ASWC2007), Busan, South Korea},
crossref = {http://data.semanticweb.org/conference/iswc-aswc/2007/proceedings},
editor = {Aberer, Karl and Choi, Key-Sun and Noy, Natasha and Allemang, Dean and Lee, Kyung-Il and Nixon, Lyndon J B and Golbeck, Jennifer and Mika, Peter and Maynard, Diana and Schreiber, Guus and Cudré-Mauroux, Philippe},
interhash = {530f5443827383077cee905d2219a21d},
intrahash = {b75014c7cf2e004bc739d0210731389e},
keywords = {2007 application_software cleanup datum extraction information iswc ontology research_02 scalable semantic_web using},
month = {November},
pages = {99-112},
publisher = {Springer Verlag},
series = {LNCS},
timestamp = {2007-11-07T19:20:51.000+0100},
title = {Scalable Cleanup of Information Extraction Data Using Ontologies},
url = {http://iswc2007.semanticweb.org/papers/99.pdf},
volume = 4825,
year = 2007
}