@inproceedings{KupietzSchonefeldWitt2015,
  author    = {Marc Kupietz and Oliver Schonefeld and Andreas Witt},
  title     = {The German Reference Corpus: New developments building on almost 50 years of experience},
  series = {Language Resources: From Storyboard to Sustainability and LR Lifecycle Management, Workshop held at the seventh conference on International Language Resources and Evaluation (LREC). Malta, May 2010},
  editor    = {Victoria Arranz and Laura van Eerten},
  publisher = {European Language Resources Association (ELRA)},
  address   = {Paris},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-45002},
  pages     = {39 -- 43},
  year      = {2015},
  abstract  = {This paper describes the efforts in the field of sustainability of the Institut f{\"u}r Deutsche Sprache (IDS) in Mannheim with respect to DEREKO (Deutsches Referenzkorpus) the Archive of General Reference Corpora of Contemporary Written German. With focus on re-usability and sustainability, we discuss its history and our future plans. We describe legal challenges related to the creation of a large and sustainable resource; sketch out the pipeline used to convert raw texts to the final corpus format and outline migration plans to TEI P5. Due to the fact, that the current version of the corpus management and query system is pushed towards its limits, we discuss the requirements for a new version which will be able to handle current and future DEREKO releases. Furthermore, we outline the institute’s plans in the field of digital preservation.},
  language  = {en}
}