@incollection{KupietzLuengenBańskietal.2014,
  author    = {Marc Kupietz and Harald L{\"u}ngen and Piotr Bański and Cyril Belica},
  title     = {Maximizing the potential of very large corpora: 50 years of big language data at IDS Mannheim},
  series = {Proceedinigs of the LREC-2014-workshop challenges in the management of large corpora (CMLC2)},
  publisher = {ELRA},
  address   = {Reykjavik},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-31634},
  pages     = {1 -- 6},
  year      = {2014},
  abstract  = {Very large corpora have been built and used at the IDS since its foundation in 1964. They have been made available on the Internet since the beginning of the 90’s to currently over 30,000 researchers worldwide. The Institute provides the largest archive of written German (Deutsches Referenzkorpus, DeReKe) which has recently been extended to 24 billion words. DeReKe has been managed and analysed by engines known as COSMAS and afterwards COSMAS II, which is currently being replaced by a new, scalable analysis platform called KorAP. KorAP makes it possible to manage and analyse texts that are accompanied by multiple, potentially conflicting, grammatical and structural annotation layers, and is able to handle resources that are distributed across different, and possibly geographically distant, storage systems. The majority of texts in DeReKe are not licensed for free redistribution, hence, the COSMAS and KorAP systems offer technical solutions to facilitate research on very large corpora that are not available (and not suitable) for download. For the new KorAP system, it is also planned to provide sandboxed environments to support non-remote-API access “near the data” through which users can run their own analysis programs.},
  language  = {en}
}