Wikipedia article names can be utilized as a controlled vocabulary for identifying the main topics in a document. Wikipedia's 2M articles cover the terminology of nearly any document collection, which permits controlled indexing in the absence of manually created vocabularies. We combine state-of-the-art strategies for automatic controlled indexing with Wikipedia's unique property—a richly hyperlinked encyclopedia. We evaluate the scheme by comparing automatically assigned topics with those chosen manually by human indexers. Analysis of indexing consistency shows that our algorithm outperforms some human subjects. 1.
%0 Generic
%1 Medelyan08keaWikipedia
%A Medelyan, Olena
%A Witten, Ian H.
%A Milne, David
%B Proceedings of the first AAAI Workshop on Wikipedia and Artificial Intelligence
%D 2008
%K 08 Medelyan content extraction kea keyphrase recommendation tag wikipedia
%T Topic Indexing with Wikipedia
%U http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.147.7850
%X Wikipedia article names can be utilized as a controlled vocabulary for identifying the main topics in a document. Wikipedia's 2M articles cover the terminology of nearly any document collection, which permits controlled indexing in the absence of manually created vocabularies. We combine state-of-the-art strategies for automatic controlled indexing with Wikipedia's unique property—a richly hyperlinked encyclopedia. We evaluate the scheme by comparing automatically assigned topics with those chosen manually by human indexers. Analysis of indexing consistency shows that our algorithm outperforms some human subjects. 1.
@electronic{Medelyan08keaWikipedia,
abstract = {Wikipedia article names can be utilized as a controlled vocabulary for identifying the main topics in a document. Wikipedia's 2M articles cover the terminology of nearly any document collection, which permits controlled indexing in the absence of manually created vocabularies. We combine state-of-the-art strategies for automatic controlled indexing with Wikipedia's unique property—a richly hyperlinked encyclopedia. We evaluate the scheme by comparing automatically assigned topics with those chosen manually by human indexers. Analysis of indexing consistency shows that our algorithm outperforms some human subjects. 1.},
added-at = {2010-10-29T02:21:45.000+0200},
author = {Medelyan, Olena and Witten, Ian H. and Milne, David},
biburl = {https://www.bibsonomy.org/bibtex/2d6058d36a97ced170d8c8aa07be22079/lee_peck},
booktitle = {Proceedings of the first AAAI Workshop on Wikipedia and Artificial Intelligence},
citeulike-article-id = {7359702},
citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.147.7850},
description = {CiteULike: Topic Indexing with Wikipedia},
interhash = {91352fc8c3493e7b520184c9ba4835a9},
intrahash = {d6058d36a97ced170d8c8aa07be22079},
keywords = {08 Medelyan content extraction kea keyphrase recommendation tag wikipedia},
posted-at = {2010-09-07 23:13:58},
priority = {2},
timestamp = {2010-10-29T02:21:45.000+0200},
title = {Topic Indexing with Wikipedia},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.147.7850},
year = 2008
}