Berners-Lee's compelling vision of a Semantic Web is hindered by a chicken-and-egg problem, which can be best solved by a bootstrapping method - creating enough structured data to motivate the development of applications. This paper argues that autonomously "Semantifying Wikipedia" is the best way to solve the problem. We choose Wikipedia as an initial data source, because it is comprehensive, not too large, high-quality, and contains enough manually-derived structure to bootstrap an autonomous, self-supervised process. We identify several types of structures which can be automatically enhanced in Wikipedia (e.g., link structure, taxonomic data, infoboxes, etc.), and we describea prototype implementation of a self-supervised, machine learning system which realizes our vision. Preliminary experiments demonstrate the high precision of our system's extracted data - in one case equaling that of humans.
%0 Journal Article
%1 Wu2007a
%A Wu, Fei
%A Weld, Daniel S
%B CIKM '07
%D 2007
%I ACM Press
%J Proc. Sixt. ACM Conf. Conf. Inf. Knowl. Manag. CIKM 07
%K information_extraction seminar ss2015 talk wikipedia
%N September 2006
%P 41
%R 10.1145/1321440.1321449
%T Autonomously Semantifying Wikipedia
%U http://portal.acm.org/citation.cfm?doid=1321440.1321449
%V pp
%X Berners-Lee's compelling vision of a Semantic Web is hindered by a chicken-and-egg problem, which can be best solved by a bootstrapping method - creating enough structured data to motivate the development of applications. This paper argues that autonomously "Semantifying Wikipedia" is the best way to solve the problem. We choose Wikipedia as an initial data source, because it is comprehensive, not too large, high-quality, and contains enough manually-derived structure to bootstrap an autonomous, self-supervised process. We identify several types of structures which can be automatically enhanced in Wikipedia (e.g., link structure, taxonomic data, infoboxes, etc.), and we describea prototype implementation of a self-supervised, machine learning system which realizes our vision. Preliminary experiments demonstrate the high precision of our system's extracted data - in one case equaling that of humans.
%@ 9781595938039
@article{Wu2007a,
abstract = {Berners-Lee's compelling vision of a Semantic Web is hindered by a chicken-and-egg problem, which can be best solved by a bootstrapping method - creating enough structured data to motivate the development of applications. This paper argues that autonomously "Semantifying Wikipedia" is the best way to solve the problem. We choose Wikipedia as an initial data source, because it is comprehensive, not too large, high-quality, and contains enough manually-derived structure to bootstrap an autonomous, self-supervised process. We identify several types of structures which can be automatically enhanced in Wikipedia (e.g., link structure, taxonomic data, infoboxes, etc.), and we describea prototype implementation of a self-supervised, machine learning system which realizes our vision. Preliminary experiments demonstrate the high precision of our system's extracted data - in one case equaling that of humans.},
added-at = {2015-06-17T22:15:48.000+0200},
author = {Wu, Fei and Weld, Daniel S},
biburl = {https://www.bibsonomy.org/bibtex/2b5b7d130b8e42bf791c5da84489a4c7c/magnuslechner},
doi = {10.1145/1321440.1321449},
institution = {ACM New York, NY, USA},
interhash = {b007780b13ba3d7c611c29a73b510f20},
intrahash = {b5b7d130b8e42bf791c5da84489a4c7c},
isbn = {9781595938039},
journal = {Proc. Sixt. ACM Conf. Conf. Inf. Knowl. Manag. CIKM 07},
keywords = {information_extraction seminar ss2015 talk wikipedia},
number = {September 2006},
pages = 41,
publisher = {ACM Press},
series = {CIKM '07},
timestamp = {2015-06-17T22:15:48.000+0200},
title = {{Autonomously Semantifying Wikipedia}},
url = {http://portal.acm.org/citation.cfm?doid=1321440.1321449},
volume = {pp},
year = 2007
}