@article{clerice-etal-2026-comma,
    title = "{C}o{MMA}, a Large-scale Corpus of Multilingual Medieval Archives",
    author = "Cl{\'e}rice, Thibault  and
      Gabay, Simon  and
      Vlachou-Efsthatiou, Malamatenia  and
      Pinche, Ariane  and
      Sagot, Beno{\^i}t",
    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.560/",
    pages = "7034--7045",
    abstract = "We present CoMMA, a large-scale corpus of medieval manuscripts produced through automatic text recognition. The corpus contains around 2.5b tokens drawn from more than 23,000 digitized manuscripts in Latin and Old French, harvested via IIIF. Unlike other resources, it is made of raw, non-normalized text enriched with layout analysis in various formats. We describe the pipeline used for large-scale acquisition and processing, and report quantitative and qualitative evaluations (average CER 9.7{\%}). The resulting resource supports multiple use cases, from pretraining language models to corpus linguistic on historical languages and digital humanities applications."
}