@inproceedings{Lange2023,
  author    = {Herbert Lange},
  title     = {Metadata formats for learner corpora: case study and discussion},
  series = {Proceedings of the 11th workshop on natural language processing for computer-assisted language learning (NLP4CALL 2022)},
  editor    = {David Alfter and Elena Volodina and Thomas Fran{\c{c}}ois and Piet Desmet and Frederik Cornillie and Arne J{\"o}nsson and Evelina Rennes},
  publisher = {LiU Electronic Press},
  address   = {Link{\"o}ping},
  isbn      = {978-91-7929-460-1},
  issn      = {1650-3740},
  doi       = {10.3384/ecp190011},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-114588},
  pages     = {108 -- 113},
  year      = {2023},
  abstract  = {Metadata provides important information relevant both to finding and understanding corpus data. Meaningful linguistic data requires both reasonable annotations and documentation of these annotations. This documentation is part of the metadata of a dataset. While corpus documentation has often been provided in the form of accompanying publications, machinereadable metadata, both containing the bibliographic information and documenting the corpus data, has many advantages. Metadata standards allow for the development of common tools and interfaces. In this paper I want to add a new perspective from an archive’s point of view and look at the metadata provided for four learner corpora and discuss the suitability of established standards for machine-readable metadata. I am are aware that there is ongoing work towards metadata standards for learner corpora. However, I would like to keep the discussion going and add another point of view: increasing findability and reusability of learner corpora in an archiving context.},
  language  = {en}
}