@inproceedings{brooks-etal-2025-annotated,
    title = "An Annotated Dataset of Errors in Premodern {G}reek and Baselines for Detecting Them",
    author = "Brooks, Creston  and
      Haubold, Johannes  and
      Cowen-Breen, Charlie  and
      White, Jay  and
      DeVaul, Desmond  and
      Riemenschneider, Frederick  and
      Narasimhan, Karthik R  and
      Graziosi, Barbara",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2025.findings-naacl.401/",
    doi = "10.18653/v1/2025.findings-naacl.401",
    pages = "7188--7202",
    ISBN = "979-8-89176-195-7",
    abstract = "As premodern texts are passed down over centuries, errors inevitably accrue. These errors can be challenging to identify, as some have survived undetected for so long precisely because they are so elusive. While prior work has evaluated error detection methods on artificially-generated errors, we introduce the first dataset of real errors in premodern Greek, enabling the evaluation of error detection methods on errors that genuinely accumulated at some stage in the centuries-long copying process. To create this dataset, we use metrics derived from BERT conditionals to sample 1,000 words more likely to contain errors, which are then annotated and labeled by a domain expert as errors or not. We then propose and evaluate new error detection methods and find that our discriminator-based detector outperforms all other methods, improving the true positive rate for classifying real errors by 5{\%}. We additionally observe that scribal errors are more difficult to detect than print or digitization errors. Our dataset enables the evaluation of error detection methods on real errors in premodern texts for the first time, providing a benchmark for developing more effective error detection algorithms to assist scholars in restoring premodern works."
}