@electronic{www.stm-assoc.org,
   title       = {Microsoft Word - 2013_11_11_Text_and_Data_Mining_Declaration.doc - 2013_11_11_Text_and_Data_Mining_Declaration.pdf}, 
   url         = {http://www.stm-assoc.org/2013_11_11_Text_and_Data_Mining_Declaration.pdf},
   biburl      = {https://puma.uni-kassel.de/url/332b7f5b1b6633c94bef77be3ccadfa5/hotho},
   keywords    = {access data dataset journal mining paper sota text},
   added-at    = {2013-11-27T08:54:41.000+0100},
   description = {},
   interhash   = {332b7f5b1b6633c94bef77be3ccadfa5}, 
   intrahash   = {332b7f5b1b6633c94bef77be3ccadfa5}
}

@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{acl-arc.comp.nus.edu.sg,
   title       = {ACL Anthology Reference Corpus (ACL ARC)}, 
   url         = {http://acl-arc.comp.nus.edu.sg/},
   biburl      = {https://puma.uni-kassel.de/url/02e1b1ee344b89910970681457820bca/hotho},
   keywords    = {acl dataset paper pdf text},
   added-at    = {2010-03-19T10:55:58.000+0100},
   description = {},
   interhash   = {02e1b1ee344b89910970681457820bca}, 
   intrahash   = {02e1b1ee344b89910970681457820bca}
}

@electronic{people.csail.mit.edu,
   title       = {Home Page for 20 Newsgroups Data Set}, 
   url         = {http://people.csail.mit.edu/jrennie/20Newsgroups/},
   biburl      = {https://puma.uni-kassel.de/url/bbb84b0f8c4f9921aaa40e1a07190279/hotho},
   keywords    = {20 dataset newsgroups text},
   added-at    = {2008-04-12T15:32:30.000+0200},
   description = {The 20 Newsgroups data set},
   interhash   = {bbb84b0f8c4f9921aaa40e1a07190279}, 
   intrahash   = {bbb84b0f8c4f9921aaa40e1a07190279}
}

@electronic{kdd.ics.uci.edu,
   title       = {20 Newsgroups}, 
   url         = {http://kdd.ics.uci.edu/databases/20newsgroups/20newsgroups.html},
   biburl      = {https://puma.uni-kassel.de/url/6ee032e41e462edbe7baf2db309d0370/hotho},
   keywords    = {20 dataset newsgroups text},
   added-at    = {2008-04-12T15:32:12.000+0200},
   description = {20 Newsgroups 


 Abstract
This data set consists of 20000 messages taken from 20 Usenet newsgroups.

 Information files:


    description of the data 


 Data files:


    20_newsgroups.tar.gz (17.3M; 61.6M uncompressed)
    mini_newsgroups.tar.gz A subset composed of 100 articles from each newsgroup. (1.9M; 6.2M uncompressed)},
   interhash   = {6ee032e41e462edbe7baf2db309d0370}, 
   intrahash   = {6ee032e41e462edbe7baf2db309d0370}
}

@electronic{mlkd.csd.auth.gr,
   title       = {Multilabel Classification}, 
   url         = {http://mlkd.csd.auth.gr/multilabel.html},
   biburl      = {https://puma.uni-kassel.de/url/ca1734ab575c5ca632a28d7b59aa4d5b/hotho},
   keywords    = {classification dataset extension multilabel text tools weka},
   added-at    = {2007-11-23T13:12:59.000+0100},
   description = {Multi-Label Classification},
   interhash   = {ca1734ab575c5ca632a28d7b59aa4d5b}, 
   intrahash   = {ca1734ab575c5ca632a28d7b59aa4d5b}
}

@electronic{aune.lpl.univ-aix.fr,
   title       = {Multext}, 
   url         = {http://aune.lpl.univ-aix.fr/projects/multext/},
   biburl      = {https://puma.uni-kassel.de/url/aadc8b8fde1c4cc4affcfa02f649f6be/hotho},
   keywords    = {corpus dataset text},
   added-at    = {2007-11-16T17:36:20.000+0100},
   description = {},
   interhash   = {aadc8b8fde1c4cc4affcfa02f649f6be}, 
   intrahash   = {aadc8b8fde1c4cc4affcfa02f649f6be}
}

@electronic{www.cs.cornell.edu,
   title       = {Datasets from transcripts of US Congressional floor debates}, 
   url         = {http://www.cs.cornell.edu/home/llee/data/convote.html},
   biburl      = {https://puma.uni-kassel.de/url/59a77db17bc3f77f9da8b3a7e0824a71/hotho},
   keywords    = {classification dataset text},
   added-at    = {2007-02-06T21:26:30.000+0100},
   description = {Congressional speech data},
   interhash   = {59a77db17bc3f77f9da8b3a7e0824a71}, 
   intrahash   = {59a77db17bc3f77f9da8b3a7e0824a71}
}

@electronic{sinai.ujaen.es,
   title       = {HepCorpus - Sinai}, 
   url         = {http://sinai.ujaen.es/wiki/index.php/HepCorpus#English_version},
   biburl      = {https://puma.uni-kassel.de/url/2a94f6d49e5f0d09fcd7d47ead339d62/hotho},
   keywords    = {text dataset corpus},
   added-at    = {2006-05-29T15:53:16.000+0200},
   description = {},
   interhash   = {2a94f6d49e5f0d09fcd7d47ead339d62}, 
   intrahash   = {2a94f6d49e5f0d09fcd7d47ead339d62}
}

@electronic{www.bmanuel.org,
   title       = {Manuel Barbera, Corpus based computational linguistic resources. General: E-Texts (§ 2.3).}, 
   url         = {http://www.bmanuel.org/clr2_et.html},
   biburl      = {https://puma.uni-kassel.de/url/35e334c2b9116aa25f7e10bed79d0347/hotho},
   keywords    = {text dataset corpus},
   added-at    = {2006-05-26T08:21:51.000+0200},
   description = {Electronic Literary Text Archives.},
   interhash   = {35e334c2b9116aa25f7e10bed79d0347}, 
   intrahash   = {35e334c2b9116aa25f7e10bed79d0347}
}

@electronic{sourceforge.net,
   title       = {SourceForge.net: Files}, 
   url         = {http://sourceforge.net/project/showfiles.php?group_id=5091&package_id=95362&release_id=399264},
   biburl      = {https://puma.uni-kassel.de/url/a81d6018be1dc1cd729c0c5e696294d9/hotho},
   keywords    = {weka text dataset},
   added-at    = {2006-03-07T08:26:04.000+0100},
   description = {New text datasets (donated by George Forman) are available for download on Sourceforge:},
   interhash   = {a81d6018be1dc1cd729c0c5e696294d9}, 
   intrahash   = {a81d6018be1dc1cd729c0c5e696294d9}
}