= Named Entity Recognition in Medieval Documents =
This page lists resources for named entity recognition in medieval documents that were developed in [https://nlp.fi.muni.cz/projects/ahisto/en the AHISTO project].

 * [https://nlp.fi.muni.cz/projects/ahisto/ner-dataset A human-annotated dataset for language modeling and named entity recognition in medieval documents]
 * Large language models for named entity recognition in medieval documents:
   * [https://huggingface.co/witiko/ahisto-ner-model-l Model L]: the largest and most accurate of the AHISTO NER models
   * [https://huggingface.co/witiko/ahisto-ner-model-s Model S]: a smaller and more efficient variant of [https://huggingface.co/witiko/ahisto-ner-model-l Model L], used in the [https://gitlab.fi.muni.cz/nlp/ahisto-modules/ner AHISTO named entity recognition tool]
   * [https://huggingface.co/witiko/ahisto-ner-model-tds1 Model TDS1] and [https://huggingface.co/witiko/ahisto-ner-model-tds2 Model TDS2]: two smaller models trained on data of different size as a part of our ablation study
   * [https://huggingface.co/witiko/ahisto-ner-model-ci Model CI]: a smaller model trained with a loss function that does not address class imbalance as a part of our ablation study
 * [https://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval Named entity experiments]: experimental code for named entity search and recognition in medieval documents
 * [https://gitlab.fi.muni.cz/nlp/ahisto-modules/ner Named entity recognition tool]: a command-line tool for named entity recognition in medieval documents, see also an [https://nlp.fi.muni.cz/projekty/ahisto/ner/ online demo] (in Czech)

== Citing ==
An article describing our dataset is currently under review. Preprint is available [mailto:witiko@mail.muni.cz on request].