@InProceedings{laguidi-EtAl:2026:DTF,
  author    = {Laâguidi, Jammila  and  Ruban, Vitaliia  and  Laarmann-Quante, Ronja  and  Drackert, Anastasia},
  title     = {DUO\_DE A1: An Annotated Corpus of Online Learning Material for Beginning Learners of German as a Foreign Language},
  booktitle      = {Proceedings of Leveraging Derived Text Formats to Unlock Copyrighted Collections for Open Science (DTF) @ LREC 2026},
  month          = {June},
  year           = {2026},
  address        = {Palma, Mallorca (Spain)},
  publisher      = {ELRA Language Resources Association (ELRA)},
  pages     = {51--62},
  abstract  = {This paper describes the creation of DUO\_DE A1, a corpus based on A1-level learning material from the Deutsch-Uni Online (DUO) language courses for German as a foreign language. We split the material into small segments and manually annotated each with fine-grained information such as the type of segment (e.g. task description, description of grammar), the medium (e.g. text, table, audio), the text units it contains (e.g. words, phrases, sentences) and other special features (e.g. marking cloze texts). Furthermore, we automatically tokenized, POS tagged and lemmatized the corpus and compared the performance of three models on these steps for different kinds of segments. We publish the created corpus in a manner that respects copyright, releasing all structural features, metadata and POS tags.},
  url       = {https://aclanthology.org/2026.dtf-1.7}
}