Deciphering an ancient script is, in general, a very complex task. Historically, the process has relied on the intuition and method of single individuals working in solitude (Jean François Champollion for Egyptian Hieroglyphs, Michael Ventris for Linear B, Henry Rawlinson for the cuneiform script), with some preparatory analysis and method laid out by previous, less celebrated, individuals (Thomas Young, Alice Kober, Georg Friedrich Grotefend, respectively). Today, we can rely on the advancement of technological progress and teamwork to mark any possible advancement in cracking ancient codes. While still about a dozen scripts remain undeciphered, we can hope to progress into deciphering them by employing both digital humanities and AI techniques. Computational methods have been applied to an extent, often in relation to one specific script. AI can be used in a multitude of ways. It is possible to investigate instances of allography by adapting unsupervised deep learning models for images to this domain. This approach does not use any prior information about the script besides attested sequences and drawings of individual signs. Another possible research direction leverages a purely symbolic representation for signs: by representing each sign as a symbol, a computer program can optimize the alignment between undeciphered scripts and one or more possible target languages. In principle, this approach could lead to the recognition of which language is transcribed by a given script, or even to some form of decipherment. In this context, digitized corpora of inscriptions are an essential prerequisite. They should offer accurate visual inspections, measuring, and virtual manipulation and analysis of textual sources and of the epigraphic media, enabling the assessment of their geometry, topology, and physical properties, and, potentially, to transcribe them even remotely. 3D digital models are the most faithful and reliable resource. Only through the synergy of these techniques can we reach unbiased and non-subjective interpretations, thus offering an effective aid to any decipherment proposal.

Ravanelli, R., Corazza, M., Lastilla, L., Tamburini, F., Ferrara, S. (2025). New Methods for Old Worlds Deciphering Ancient Scripts: Integrated, State-of-the-Art Approaches. London : Routledge [10.4324/9781003584155-13].

New Methods for Old Worlds Deciphering Ancient Scripts: Integrated, State-of-the-Art Approaches

Corazza M.;Lastilla L.;Tamburini F.;Ferrara S.
2025

Abstract

Deciphering an ancient script is, in general, a very complex task. Historically, the process has relied on the intuition and method of single individuals working in solitude (Jean François Champollion for Egyptian Hieroglyphs, Michael Ventris for Linear B, Henry Rawlinson for the cuneiform script), with some preparatory analysis and method laid out by previous, less celebrated, individuals (Thomas Young, Alice Kober, Georg Friedrich Grotefend, respectively). Today, we can rely on the advancement of technological progress and teamwork to mark any possible advancement in cracking ancient codes. While still about a dozen scripts remain undeciphered, we can hope to progress into deciphering them by employing both digital humanities and AI techniques. Computational methods have been applied to an extent, often in relation to one specific script. AI can be used in a multitude of ways. It is possible to investigate instances of allography by adapting unsupervised deep learning models for images to this domain. This approach does not use any prior information about the script besides attested sequences and drawings of individual signs. Another possible research direction leverages a purely symbolic representation for signs: by representing each sign as a symbol, a computer program can optimize the alignment between undeciphered scripts and one or more possible target languages. In principle, this approach could lead to the recognition of which language is transcribed by a given script, or even to some form of decipherment. In this context, digitized corpora of inscriptions are an essential prerequisite. They should offer accurate visual inspections, measuring, and virtual manipulation and analysis of textual sources and of the epigraphic media, enabling the assessment of their geometry, topology, and physical properties, and, potentially, to transcribe them even remotely. 3D digital models are the most faithful and reliable resource. Only through the synergy of these techniques can we reach unbiased and non-subjective interpretations, thus offering an effective aid to any decipherment proposal.
2025
Evolving Perspectives on Digital Classics
159
180
Ravanelli, R., Corazza, M., Lastilla, L., Tamburini, F., Ferrara, S. (2025). New Methods for Old Worlds Deciphering Ancient Scripts: Integrated, State-of-the-Art Approaches. London : Routledge [10.4324/9781003584155-13].
Ravanelli, R.; Corazza, M.; Lastilla, L.; Tamburini, F.; Ferrara, S.
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/1033537
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact