Restoring ancient text using deep learning: a case study on Greek epigraphy

@inproceedings{Assael2019RestoringAT,
  title={Restoring ancient text using deep learning: a case study on Greek epigraphy},
  author={Yannis M. Assael and Thea Sommerschield and J. Prag},
  booktitle={EMNLP/IJCNLP},
  year={2019}
}
  • Yannis M. Assael, Thea Sommerschield, J. Prag
  • Published in EMNLP/IJCNLP 2019
  • Computer Science
  • Ancient History relies on disciplines such as Epigraphy, the study of ancient inscribed texts, for evidence of the recorded past. However, these texts, “inscriptions”, are often damaged over the centuries, and illegible parts of the text must be restored by specialists, known as epigraphists. This work presents Pythia, the first ancient text restoration model that recovers missing characters from a damaged text input using deep neural networks. Its architecture is carefully designed to handle… CONTINUE READING
    7 Citations

    Topics from this paper.

    Restoration of fragmentary Babylonian texts using recurrent neural networks
    Ancient Korean Neural Machine Translation
    Enabling Language Models to Fill in the Blanks
    • 14
    • PDF
    Blank Language Models
    • 5
    • Highly Influenced
    • PDF
    Latin BERT: A Contextual Language Model for Classical Philology
    The computerization of archaeology: survey on AI techniques

    References

    SHOWING 1-10 OF 38 REFERENCES
    Deep Learning the Indus Script
    • 2
    • PDF
    Optical Character Recognition for Sanskrit Using Convolution Neural Networks
    • Avadesh Meduri, N. Goyal
    • Computer Science
    • 2018 13th IAPR International Workshop on Document Analysis Systems (DAS)
    • 2018
    • 14
    A Markov model of the Indus script
    • 34
    • PDF
    Sequence to Sequence Learning with Neural Networks
    • 10,950
    • PDF
    Character-Aware Neural Language Models
    • 1,210
    • PDF