This code is used for the paper "Is Text Normalization Relevant for Classifying Medieval Charters?". The official proceedings are available at https://doi.org/10.1007/978-3-031-72440-4_12; the preprint is available at https://arxiv.org/abs/2408.16446. The repository will be regularly updated, extended, and tagged accordingly.
The initial dataset was prepared as referenced in our work, and includes id, abstract, text, year. Columns supercuration and decade were additionally provided by the project DiDip. The final dataset is found in data/.
The work presented in this paper has been supported by the ERC Advanced Grant project (101019327) “From Digital to Distant Diplomatics”.