@electronic{github.com,
   title       = {jgilme1/CorpusProcessing-Hadoop-Multir · GitHub}, 
   url         = {https://github.com/jgilme1/CorpusProcessing-Hadoop-Multir},
   biburl      = {https://puma.uni-kassel.de/url/18a92cdb5b13df298a5aa02bd4b9ecaa/hotho},
   keywords    = {hadoop nlp parsing},
   added-at    = {2015-01-27T14:55:58.000+0100},
   description = {CorpusProcessing-Hadoop-Multir - This is a collection of Hadoop jobs I used to process a Corpus of ~1M documents for input to Multir training.},
   interhash   = {18a92cdb5b13df298a5aa02bd4b9ecaa}, 
   intrahash   = {18a92cdb5b13df298a5aa02bd4b9ecaa}
}

@electronic{www.datacommunitydc.org,
   title       = {Python's Natural Language Took Kit (NLTK) and Hadoop - Part 3 — Data Community DC}, 
   url         = {http://www.datacommunitydc.org/blog/2013/05/nltk-hadoop},
   biburl      = {https://puma.uni-kassel.de/url/8535b059b2dbe6fb23fafb9a7810d4a6/hotho},
   keywords    = {hadoop natural nlp pythons},
   added-at    = {2015-01-27T14:54:29.000+0100},
   description = { },
   interhash   = {8535b059b2dbe6fb23fafb9a7810d4a6}, 
   intrahash   = {8535b059b2dbe6fb23fafb9a7810d4a6}
}

@electronic{www.r-bloggers.com,
   title       = {Julia, I Love You | (R news & tutorials)}, 
   url         = {http://www.r-bloggers.com/julia-i-love-you/},
   biburl      = {https://puma.uni-kassel.de/url/be555060c87db7b798ce4afa21537e7e/hotho},
   keywords    = {computing fast hadoop language parallel programming rechnen scientific},
   added-at    = {2013-02-01T11:54:59.000+0100},
   description = {},
   interhash   = {be555060c87db7b798ce4afa21537e7e}, 
   intrahash   = {be555060c87db7b798ce4afa21537e7e}
}

@electronic{www.umiacs.umd.edu,
   title       = {Ivory: A Hadoop toolkit for web-scale information retrieval research}, 
   url         = {http://www.umiacs.umd.edu/~jimmylin/ivory/docs/index.html},
   biburl      = {https://puma.uni-kassel.de/url/a96c0424ab048039c57ac3288994b65b/hotho},
   keywords    = {hadoop ir ivory toolkit tools},
   added-at    = {2011-09-22T13:51:15.000+0200},
   description = {},
   interhash   = {a96c0424ab048039c57ac3288994b65b}, 
   intrahash   = {a96c0424ab048039c57ac3288994b65b}
}

@electronic{www.elasticsearch.org,
   title       = {elasticsearch - - Open Source, Distributed, RESTful, Search Engine}, 
   url         = {http://www.elasticsearch.org/},
   biburl      = {https://puma.uni-kassel.de/url/5384764a16fab767ebcbc17d87758a24/hotho},
   keywords    = {distributed hadoop lucene open source},
   added-at    = {2011-03-30T11:00:19.000+0200},
   description = {elasticsearch},
   interhash   = {5384764a16fab767ebcbc17d87758a24}, 
   intrahash   = {5384764a16fab767ebcbc17d87758a24}
}

@electronic{www.heise.de,
   title       = {heise Developer - 01.04.2010 08:58 - Verarbeiten großer verteilter Datenmengen mit Hadoop}, 
   url         = {http://www.heise.de/developer/artikel/Verarbeiten-grosser-verteilter-Datenmengen-mit-Hadoop-964755.html},
   biburl      = {https://puma.uni-kassel.de/url/fe7bcc86e8ba4603c0a499ac78f0ff18/hotho},
   keywords    = {developer hadoop heise open source},
   added-at    = {2010-04-01T10:35:27.000+0200},
   description = {Internetfirmen müssen für den Betrieb ihrer Dienste täglich Datenmengen im Giga- und Petabereich speichern und effizient verarbeiten. Den Part der Datenverarbeitung können Googles MapReduce oder die Open-Source-Nachbildung Hadoop übernehmen.},
   interhash   = {fe7bcc86e8ba4603c0a499ac78f0ff18}, 
   intrahash   = {fe7bcc86e8ba4603c0a499ac78f0ff18}
}