Lacunae

Automatic Filling of Greek and Latin Epigraphic Gaps

The aim of the LACUNAE project is the development of a digital tool that uses artificial intelligence to generate suggestions for the integration of lacunae in Greek and Latin epigraphic documents based on a comparison with selected epigraphic and literary sources. The tool will be implemented according to the principles of XAI (eXplainable Artificial Intelligence), i.e., using a technology that makes the process of AI integration comprehensible to the user.

As far as Latin inscriptions are concerned, the project focuses on public epigraphic documents from the Roman Imperial period; in its Greek branch, it addresses documents from the Archaic-Classical period written in different dialectal and alphabetic varieties. In both cases, the project aims to adapt and apply, with some improvements, the model developed for Greek inscriptions in the Ithaca project, as well as the models Latin BERT for Latin literary texts, and Ancient Greek BERT for Greek literary texts.

References

2024

  1. AI for the Restoration of Ancient Inscriptions: A Computational Linguistics Perspective
    Alessandro Locaputo, Beatrice Portelli, Stefano Magnani, and 2 more authors
    In Decoding Cultural Heritage: A Critical Dissection and Taxonomy of Human Creativity Through Digital Tools, 2024
    In Publishing Phase

2023

  1. Filling the Lacunae in ancient Latin inscriptions
    A. Locaputo, B Portelli, E Colombi, and 1 more author
    In Proceedings of the 19th Conference on Information and Research Science Connecting to Digital and Library Science, 2023
  2. Usage of Language Model for the Filling of Lacunae in Ancient Latin Inscriptions: A Case Study
    Andrea Brunello, Emanuela Colombi, Alessandro Locaputo, and 3 more authors
    In Proceedings of the 2nd Workshop on Artificial Intelligence for Cultural Heritage (IAI4CH 2023), 2023