Explainable dating of greek papyri images

Greek literary papyri, which are unique witnesses of antique literature, do not usually bear a date. They are thus currently dated based on palaeographical methods, with broad approximations which often span more than a century. We created a dataset of 242 images of papyri written in “bookhand” scri...

Description complète

Enregistré dans:
Détails bibliographiques
Auteurs principaux: Pavlopoulos, John (Auteur) , Konstantinidou, Maria (Auteur) , Perdiki, Elpida (Auteur) , Marthot-Santaniello, Isabelle (Auteur) , Essler, Holger (Auteur) , Vardakas, Georgios (Auteur) , Likas, Aristidis (Auteur)
Format: Article (Journal)
Langue:anglais
Publié: 11 July 2024
In: Machine learning
Year: 2024, Volume: 113, Numéro: 9, Pages: 6765-6786
ISSN:1573-0565
DOI:10.1007/s10994-024-06589-w
Accès en ligne:Verlag, kostenfrei, Volltext: https://doi.org/10.1007/s10994-024-06589-w
Accéder au texte intégral
Notes sur l'auteur:John Pavlopoulos, Maria Konstantinidou, Elpida Perdiki, Isabelle Marthot-Santaniello, Holger Essler, Georgios Vardakas, Aristidis Likas
Description
Résumé:Greek literary papyri, which are unique witnesses of antique literature, do not usually bear a date. They are thus currently dated based on palaeographical methods, with broad approximations which often span more than a century. We created a dataset of 242 images of papyri written in “bookhand” scripts whose date can be securely assigned, and we used it to train algorithms for the task of dating, showing its challenging nature. To address data scarcity, we extended our dataset by segmenting each image into its respective text lines. By using the line-based version of our dataset, we trained a Convolutional Neural Network, equipped with a fragmentation-based augmentation strategy, and we achieved a mean absolute error of 54 years. The results improve further when the task is cast as a multi-class classification problem, predicting the century. Using our network, we computed precise date estimations for papyri whose date is disputed or vaguely defined, employing explainability to understand dating-driving features.
Description:Gesehen am 08.07.2026
Description matérielle:Online Resource
ISSN:1573-0565
DOI:10.1007/s10994-024-06589-w