@article{d-souza-etal-2026-extreme,
    title = "An Extreme Multi-label Text Classification ({XMTC}) Library Dataset: What If We Took ``Use of Practical {AI} in Digital Libraries'' Seriously?",
    author = "D'Souza, Jennifer  and
      Sadruddin, Sameer  and
      Kaehler, Maximilian  and
      Salfinger, Andrea  and
      Zaccagna, Luca  and
      Incitti, Francesca  and
      Snidaro, Lauro  and
      Suominen, Osma",
    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.12/",
    pages = "169--184",
    abstract = "Subject indexing is vital for discovery but hard to sustain at scale and across languages. We release a large bilingual (English/German) corpus of catalog records annotated with the Integrated Authority File (GND), plus a machine-actionable GND taxonomy. The resource enables ontology-aware multi-label classification, mapping text to authority terms, and agent-assisted cataloging with reproducible, authority-grounded evaluation. We provide a brief statistical profile and qualitative error analyses of three systems. We invite the community to assess not only accuracy but usefulness and transparency, toward authority-anchored AI co-pilots that amplify catalogers' work."
}