@inproceedings{messner-lippincott-2024-pairing,
    title = "Pairing Orthographically Variant Literary Words to Standard Equivalents Using Neural Edit Distance Models",
    author = "Messner, Craig  and
      Lippincott, Thomas",
    editor = "Bizzoni, Yuri  and
      Degaetano-Ortlieb, Stefania  and
      Kazantseva, Anna  and
      Szpakowicz, Stan",
    booktitle = "Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024)",
    month = mar,
    year = "2024",
    address = "St. Julians, Malta",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.latechclfl-1.26/",
    pages = "264--269",
    abstract = "We present a novel corpus consisting of orthographically variant words found in works of 19th century U.S. literature annotated with their corresponding {\textquotedblleft}standard{\textquotedblright} word pair. We train a set of neural edit distance models to pair these variants with their standard forms, and compare the performance of these models to the performance of a set of neural edit distance models trained on a corpus of orthographic errors made by L2 English learners. Finally, we analyze the relative performance of these models in the light of different negative training sample generation strategies, and offer concluding remarks on the unique challenge literary orthographic variation poses to string pairing methodologies."
}