@inproceedings{hopton-etal-2026-mediomatix,
    title = "The Mediomatix Corpus: Parallel Data for {R}omansh Language Varieties via Comparable Schoolbooks",
    author = {Hopton, Zachary William  and
      Vamvas, Jannis  and
      B{\"u}chler, Andrin  and
      Rutkiewicz, Anna  and
      Cathomas, Rico  and
      Sennrich, Rico},
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.findings-eacl.16/",
    pages = "290--306",
    ISBN = "979-8-89176-386-9",
    abstract = "The five idioms (i.e., varieties) of the Romansh language are largely standardized and are taught in the schools of the respective communities in Switzerland. In this paper, we present the first parallel corpus of Romansh idioms. The corpus is based on 291 schoolbook volumes, which are comparable in content for the five idioms. We use automatic alignment methods to extract 207k multi-parallel segments from the books, with more than 2M tokens in total. A small-scale human evaluation confirms that the segments are highly parallel, making the dataset suitable for NLP applications such as machine translation between Romansh idioms. We release the parallel and unaligned versions of the dataset under a CC-BY-NC-SA license and demonstrate its utility for machine translation by training and evaluating an LLM and a supervised multilingual MT model on the dataset."
}