Kernel Methods for Mining Instance Data in Ontologies
S. Bloehdorn, and Y. Sure. Proceedings of the 6th International Semantic Web Conference and 2nd Asian Semantic Web Conference (ISWC/ASWC2007), Busan, South Korea, volume 4825 of LNCS, page 57--70. Berlin, Heidelberg, Springer Verlag, (November 2007)
Abstract
The amount of ontologies and meta data available on the Web is constantly growing. The successful application of machine learning techniques for learning of ontologies from textual data, i.e. mining for the Semantic Web, contributes to this trend. However, no principal approaches exist so far for mining from the Semantic Web. We investigate how machine learning algorithms can be made amenable for directly taking advantage of the rich knowledge expressed in ontologies and associated instance data. Kernel methods have been successfully employed in various learning tasks and provide a clean framework for interfacing between non-vectorial data and machine learning algorithms. In this spirit, we express the problem of mining instances in ontologies as the problem of defining valid corresponding kernels. We present a principled framework for designing such kernels by means of decomposing the kernel computation into specialized kernels for selected characteristics of an ontology which can be flexibly assembled and tuned. Initial experiments on real world Semantic Web data enjoy promising results and show the usefulness of our approach.
%0 Conference Paper
%1 Bloehdorn/2007/Kernel
%A Bloehdorn, Stephan
%A Sure, York
%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 data_management datum instance iswc kernel method mining ontology research_13 semantic_web
%P 57--70
%T Kernel Methods for Mining Instance Data in Ontologies
%U http://iswc2007.semanticweb.org/papers/57.pdf
%V 4825
%X The amount of ontologies and meta data available on the Web is constantly growing. The successful application of machine learning techniques for learning of ontologies from textual data, i.e. mining for the Semantic Web, contributes to this trend. However, no principal approaches exist so far for mining from the Semantic Web. We investigate how machine learning algorithms can be made amenable for directly taking advantage of the rich knowledge expressed in ontologies and associated instance data. Kernel methods have been successfully employed in various learning tasks and provide a clean framework for interfacing between non-vectorial data and machine learning algorithms. In this spirit, we express the problem of mining instances in ontologies as the problem of defining valid corresponding kernels. We present a principled framework for designing such kernels by means of decomposing the kernel computation into specialized kernels for selected characteristics of an ontology which can be flexibly assembled and tuned. Initial experiments on real world Semantic Web data enjoy promising results and show the usefulness of our approach.
@inproceedings{Bloehdorn/2007/Kernel,
abstract = {The amount of ontologies and meta data available on the Web is constantly growing. The successful application of machine learning techniques for learning of ontologies from textual data, i.e. mining for the Semantic Web, contributes to this trend. However, no principal approaches exist so far for mining from the Semantic Web. We investigate how machine learning algorithms can be made amenable for directly taking advantage of the rich knowledge expressed in ontologies and associated instance data. Kernel methods have been successfully employed in various learning tasks and provide a clean framework for interfacing between non-vectorial data and machine learning algorithms. In this spirit, we express the problem of mining instances in ontologies as the problem of defining valid corresponding kernels. We present a principled framework for designing such kernels by means of decomposing the kernel computation into specialized kernels for selected characteristics of an ontology which can be flexibly assembled and tuned. Initial experiments on real world Semantic Web data enjoy promising results and show the usefulness of our approach.},
added-at = {2007-11-07T19:13:58.000+0100},
address = {Berlin, Heidelberg},
author = {Bloehdorn, Stephan and Sure, York},
biburl = {https://www.bibsonomy.org/bibtex/2f070ebca542ef032552bc69eef8c93b9/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 = {b117a5803b843dc3c214af5b2bf3cb1d},
intrahash = {f070ebca542ef032552bc69eef8c93b9},
keywords = {2007 application_software data_management datum instance iswc kernel method mining ontology research_13 semantic_web},
month = {November},
pages = {57--70},
publisher = {Springer Verlag},
series = {LNCS},
timestamp = {2007-11-07T19:20:51.000+0100},
title = {Kernel Methods for Mining Instance Data in Ontologies},
url = {http://iswc2007.semanticweb.org/papers/57.pdf},
volume = 4825,
year = 2007
}