NEWS

Ven 13 Dic 2024

Presentazione del volume di scritti di Lucia Criscuolo

Bologna, 13 dicembre 2024, 17.30

leggi
Lun 02 Dic 2024

SAEG IX - Seminario Avanzato di Epigrafia Greca 2025

Roma, 8-10 gennaio 2025 Programma

leggi
Mer 13 Nov 2024

ENCODING METRICAL INSCRIPTIONS

 Foggia, 14-15 novembre 2024

leggi

RESOCONTI

Mar 25 Giu 2019

Bologna EpiDoc Workshop 2019

Bologna, 27-31 maggio 2019

Resoconto di Matteo Rivoli

leggi
Gio 09 Feb 2017

SAEG 5° Seminario Avanzato di Epigrafia Greca

Torino, 18-20 gennaio 2017

Resoconto di Francesca Giovagnorio

leggi
Lun 10 Ott 2016

EpiDoc Workshop Bologna 2016

Bologna, 12-14 settembre 2016

Resoconto di Irene Nicolino

leggi

Restoring and attributing ancient texts using deep neural networks

Gio 10 Marzo 2022

 Nature, 9.3.2022

We share the announcement of a new publication, titled “Restoring and attributing ancient texts using deep neural networks”, published on the cover of this week's issue of the scientific journal Nature. This work is the result of a collaboration between the Universities of Venice Ca’ Foscari, Oxford and Athens AUEB, and Google’s DeepMind.

The article presents Ithaca, the first deep neural network that can aid historians in not only restoring the missing text of ancient Greek inscriptions, but also identifying their original location, and establishing the date they were written.

Ithaca is designed to assist and expand the historian’s workflow: its architecture focuses on collaboration, decision support, and interpretability. Working alone, Ithaca is able to restore damaged texts with a 62% accuracy, but when evaluated historians use Ithaca, their accuracy on the same task rises to 72%. Ithaca can also determine the original geographical location of inscriptions with 71% accuracy, and can date them to less than 30 years from the date ranges proposed by historians, redating key texts of Classical Athens and contributing to topical debates in Ancient History.
This work shows how models like Ithaca can unlock the cooperative potential between AI and historians, transformationally impacting the way we study and write about one of the most significant periods in human history.

To make the research widely available to researchers, educators, museum staff and others, the authors partnered with Google Cloud and Google Arts & Culture to launch a free interactive version of Ithaca and also open sourced the code.

Links:
Link to published paper (open access): https://www.nature.com/articles/s41586-022-04448-z
Link to Ithaca’s free online interface: https://ithaca.deepmind.com
Link to Nature's announcement video: https://www.youtube.com/watch?v=rq0Ex_qCKeQ
Link to Ca' Foscari's press release (in Italian): https://www.unive.it/pag/14024/?tx_news_pi1%5Bnews%5D=12038&cHash=ee3ef41bb70b14cbda7f8dba3f65f07f
Link to the open source code: https://github.com/deepmind/ithaca


Ithaca's authors: Yannis Assael*, Thea Sommerschield*, Brendan Shillingford, Mahyar Bordbar, John Pavlopoulos, Marita Chatzipanagiotou, Ion Androutsopoulos, Jonathan Prag & Nando de Freitas.

SITEG - Sito Italiano di Epigrafia Greca
Dipartimento di Storia Antica
via Zamboni 38 - 40126 Bologna
+39.051.2098391 - mail: info@siteg.it
SITEG © 2024 - Webdesign Ideaedi.it