@article{thielen-kugler-2026-amdi,
    title = "{A}m{D}i - Ambiguous Words Diachronic Dataset",
    author = "Thielen, Felix  and
      Kugler, Kai",
    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.934/",
    pages = "11926--11941",
    abstract = "Two fundamental tasks in computational linguistics are Lexical Semantic Change Detection and Word Sense Disambiguation. Both commonly rely on large annotated datasets. Most available datasets cover only one of two areas: diachronic corpora used for Semantic Change Detection, or synchronic datasets for Word Sense Disambiguation. To address this gap, the AmDi dataset is introduced as a German-language resource that supports a more fine-grained diachronic analysis of word meanings, while also enabling the investigation of embeddings generated with corresponding models, as well as providing a foundation for Word Sense Disambiguation tasks."
}