@inproceedings{dinu-etal-2024-verba,
    title = "Verba volant, scripta volant? Don{'}t worry! There are computational solutions for protoword reconstruction",
    author = "Dinu, Liviu P  and
      Uban, Ana Sabina  and
      Cristea, Alina Maria  and
      Iordache, Ioan-Bogdan  and
      Marchitan, Teodor-George  and
      Georgescu, Simona  and
      Zoicas, Laurentiu",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.362/",
    doi = "10.18653/v1/2024.emnlp-main.362",
    pages = "6314--6326",
    abstract = "We introduce a new database of cognate words and etymons for the five main Romance languages, the most comprehensive one to date. We propose a strong benchmark for the automatic reconstruction of protowords for Romance languages, by applying a set of machine learning models and features on these data. The best results reach 90{\%} accuracy in predicting the protoword of a given cognate set, surpassing existing state-of-the-art results for this task and showing that computational methods can be very useful in assisting linguists with protoword reconstruction."
}