@inproceedings{hamotskyi-etal-2024-fincorpus,
    title = "{F}in{C}orpus-{DE}10k: A Corpus for the {G}erman Financial Domain",
    author = {Hamotskyi, Serhii  and
      Kozaeva, Nata  and
      H{\"a}nig, Christian},
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.lrec-main.639/",
    pages = "7277--7285",
    abstract = "We introduce a predominantly German corpus comprising 12.5k PDF documents sourced from the financial domain. The corresponding extracted textual data encompasses more than 165 million tokens derived predominantly from German, and to a lesser extent, bilingual documents. We provide detailed information about the document types included in the corpus, such as final terms, base prospectuses, annual reports, information materials, law documents, international financial reporting standards, and monthly reports from the Bundesbank, accompanied by comprehensive statistical analysis. To our knowledge, it is the first non-email German financial corpus available, and we hope it will fill this gap and foster further research in the financial domain both in the German language and in multilingual contexts."
}