@article{chiarcos-etal-2026-building,
    title = "Building the {AURIS} Corpus of Reference and Information Structure",
    author = {Chiarcos, Christian  and
      F{\"a}th, Christian  and
      Gr{\"o}ger, Tabea  and
      Frey, Quentin Alastair},
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.160/",
    pages = "2035--2047",
    abstract = "We present AURIS, the Augsburg corpus for Reference and Information Structure, a multilingual corpus annotated for reference, discourse relations, and aspects of information structure. AURIS introduces an innovative use of off-the-shelf spreadsheet software for complex annotation tasks, reducing technical barriers and dependencies common in discourse annotation. Designed for classroom use, it enables linguistics and philology students to explore diverse theoretical frameworks while working in their language of choice. The paper focuses on technical design and workflows that integrate and generate pre-annotations from heterogeneous sources. Despite its low-tech approach, AURIS aligns with established standards and remains interoperable with existing projects. Preprocessing scripts support multiple languages, with an initial annotation round on German texts evaluated against TED-MDB and ParCorFull data converted into AURIS formats. This approach demonstrates that accessible tools can yield high-quality, replicable annotations for discourse and information-structure research."
}