@incollection{HedelandSchmidt2020,
  author    = {Hanna Hedeland and Thomas Schmidt},
  title     = {Technological and methodological challenges in creating, annotating and sharing a learner corpus of spoken German},
  series = {Multilingual Corpora and Multilingual Corpus Analysis},
  editor    = {Thomas Schmidt and Kai W{\"o}rner},
  publisher = {Benjamins},
  address   = {Amsterdam},
  isbn      = {9789027219343},
  doi       = {10.1075/hsm.14.04hed},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-97229},
  pages     = {25 -- 46},
  year      = {2020},
  abstract  = {This article discusses questions concerning the creation, annotation and sharing of spoken language corpora. We use the Hamburg Map Task Corpus (HAMATAC), a small corpus in which advanced learners of German were recorded solving a map task, as an example to illustrate our main points. We first give an overview of the corpus creation and annotation process including recording, metadata documentation, transcription and semi-automatic annotation of the data. We then discuss the manual annotation of disfluencies as an example case in which many of the typical and challenging problems for data reuse – in particular the reliability of interpretative annotations – are revealed.},
  language  = {en}
}