@electronic{www.yr-bcn.es, title = {semantically_annotated_snapshot_of_wikipedia}, url = {http://www.yr-bcn.es/semanticWikipedia}, biburl = {https://puma.uni-kassel.de/url/a703bcf3b3890f8a4a61f052228bae8f/hotho}, keywords = {tagging dataset wikipedia semantic pos}, added-at = {2009-04-09T10:41:38.000+0200}, description = {}, interhash = {a703bcf3b3890f8a4a61f052228bae8f}, intrahash = {a703bcf3b3890f8a4a61f052228bae8f} } @electronic{lshtc.iit.demokritos.gr, title = {Call for Participation | Second Pascal Challenge on Large Scale Hierarchical Text classification}, url = {http://lshtc.iit.demokritos.gr/}, biburl = {https://puma.uni-kassel.de/url/473be765bc5416cd619de9e7ac5e40bf/benz}, keywords = {2011 challenge dataset dmoz text_classification wikipedia workshop}, added-at = {2011-02-04T16:06:38.000+0100}, description = {Following a successful first edition, we are pleased to announce the 2nd edition of the Large Scale Hierarchical Text Classification (LSHTC) Pascal Challenge. The LSHTC Challenge is a hierarchical text classification competition, using large datasets. This year’s challenge will increase the scale and the difficulty of the task, using data from Wikipedia (www.wikipedia.org), in addition to the ODP Web directory data (www.dmoz.org).}, interhash = {473be765bc5416cd619de9e7ac5e40bf}, intrahash = {473be765bc5416cd619de9e7ac5e40bf} } @electronic{evanjones.ca, title = {Extracting Text from Wikipedia}, url = {http://evanjones.ca/software/wikipedia2text.html}, biburl = {https://puma.uni-kassel.de/url/7ee155b9d5b03240e99556cbf828f202/benz}, keywords = {data dataset plain_text python text tool wiki wikipedia}, added-at = {2011-02-04T16:07:25.000+0100}, description = {}, interhash = {7ee155b9d5b03240e99556cbf828f202}, intrahash = {7ee155b9d5b03240e99556cbf828f202} } @electronic{www.eml-research.de, title = {Download Wikipedia Category Taxonomy}, url = {http://www.eml-research.de/english/research/nlp/download/wikitaxonomy.php}, biburl = {https://puma.uni-kassel.de/url/9d33bae08b8defaa95cda39608876bf6/benz}, keywords = {categories category_hierarchy dataset download hierarchy ontology taxonomy wikipedia}, added-at = {2011-02-04T16:07:33.000+0100}, description = {}, interhash = {9d33bae08b8defaa95cda39608876bf6}, intrahash = {9d33bae08b8defaa95cda39608876bf6} } @electronic{www.yr-bcn.es, title = {Semantically Annotated Snapshot of the English Wikipedia (SW v.1)}, url = {http://www.yr-bcn.es/semanticWikipedia}, biburl = {https://puma.uni-kassel.de/url/a703bcf3b3890f8a4a61f052228bae8f/benz}, keywords = {semantics dataset wikipedia annotated ontology}, added-at = {2011-02-04T16:08:40.000+0100}, description = {}, interhash = {a703bcf3b3890f8a4a61f052228bae8f}, intrahash = {a703bcf3b3890f8a4a61f052228bae8f} } @electronic{googleresearch.blogspot.de, title = {Learning from Big Data: 40 Million Entities in Context}, url = {http://googleresearch.blogspot.de/2013/03/learning-from-big-data-40-million.html}, biburl = {https://puma.uni-kassel.de/url/14073030361b1ef9cfcc6881845c9a28/hotho}, keywords = {40 data dataset learning million wikipedia}, added-at = {2013-03-11T09:42:06.000+0100}, description = {}, interhash = {14073030361b1ef9cfcc6881845c9a28}, intrahash = {14073030361b1ef9cfcc6881845c9a28} } @electronic{ewulczyn.github.io, title = {Wikipedia Clickstream - Getting Started – Ellery Wulczyn – Research Analyst at The Wikimedia Foundation}, url = {http://ewulczyn.github.io/Wikipedia_Clickstream_Getting_Started/}, biburl = {https://puma.uni-kassel.de/url/d3111e6af4618baedf03d556572e54d5/hotho}, keywords = {clickstream dataset file log wikipedia}, added-at = {2015-03-09T08:27:02.000+0100}, description = {Research Analyst at The Wikimedia Foundation}, interhash = {d3111e6af4618baedf03d556572e54d5}, intrahash = {d3111e6af4618baedf03d556572e54d5} }