@inproceedings{ArnoldFisseniKamockietal.2020,
  author    = {Denis Arnold and Bernhard Fisseni and Paweł Kamocki and Oliver Schonefeld and Marc Kupietz and Thomas Schmidt},
  title     = {Addressing Cha(lle)nges in Long-Term Archiving of Large Corpora},
  series = {Proceedings of the LREC 2020 Workshop, Language Resources and Evaluation Conference, 11–16 May 2020, 8th Workshop on Challenges in the Management of Large Corpora (CMLC-8)},
  editor    = {Piotr Bański and Adrien Barbaresi and Simon Clematide and Marc Kupietz and Harald L{\"u}ngen and Ines Pisetta},
  publisher = {European Language Resources Association},
  address   = {Paris},
  isbn      = {979-10-95546-61-0},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-98129},
  pages     = {1 -- 9},
  year      = {2020},
  abstract  = {This paper addresses long-term archival for large corpora. Three aspects specific to language resources are focused, namely (1) the removal of resources for legal reasons, (2) versioning of (unchanged) objects in constantly growing resources, especially where objects can be part of multiple releases but also part of different collections, and (3) the conversion of data to new formats for digital preservation. It is motivated why language resources may have to be changed, and why formats may need to be converted. As a solution, the use of an intermediate proxy object called a signpost is suggested. The approach will be exemplified with respect to the corpora of the Leibniz Institute for the German Language in Mannheim, namely the German Reference Corpus (DeReKo) and the Archive for Spoken German (AGD).},
  language  = {en}
}