@inproceedings{nordhoff-2025-creating,
    title = "Creating and enriching a repository of 177k interlinearized examples in 1611 mostly lesser-resourced languages",
    author = "Nordhoff, Sebastian",
    editor = "Alam, Mehwish  and
      Tchechmedjiev, Andon  and
      Gracia, Jorge  and
      Gromann, Dagmar  and
      di Buono, Maria Pia  and
      Monti, Johanna  and
      Ionov, Maxim",
    booktitle = "Proceedings of the 5th Conference on Language, Data and Knowledge",
    month = sep,
    year = "2025",
    address = "Naples, Italy",
    publisher = "Unior Press",
    url = "https://preview.aclanthology.org/ldl-25-ingestion/2025.ldk-1.20/",
    pages = "186--196",
    ISBN = "978-88-6719-333-2",
    abstract = "29 Much of NLP is concerned with languages for which dictionaries, thesauri, word nets or treebanks are available. This contribution focuses on languages for which all we have might be some isolated examples with word-to-word translation. We detail the collection, aggregation, storage and querying of this database of 177k examples from 1611 languages with a special eye on enrichment via Named Entity Recognition and links to the Wikidata ontology. We also discuss pitfalls of the approach and discuss the legal status of interlinear examples."
}