Many ancient populations used inscriptions(铭文) to document different parts of their lives. But the objects containing such inscriptions have been damaged over the centuries.
The researchers, led by Alphabet's AI company DeepMind, developed a new AI-based method which serves as a technological tool to help researchers repair missing inscriptions and estimate the true origins of the records. They call their tool Ithaca. The system is the first deep neural(神经的)network that can restore the missing text of damaged inscriptions. The researchers said it trained Ithaca on the largest collection of data containing Greek inscriptions from the non-profit Packard Humanities Institute in California. Feeding this data into the system is designed to help the tool use past writings to predict missing letters and words in damaged inscriptions.
The researchers reported that in experiments with damaged writings, Ithaca was able to correctly predict missing inscription elements 62% of the time. In addition, the tool was 71% correct in identifying where the inscriptions first came from. And when historians work on their own, the success rate for restoring damaged inscriptions is about 25%. But when humans teamed up with Ithaca to assist in their work, the success rate jumped to 72%.
Thea Sommerschield from Ca'Foscari University of Venice said the system had already provided new information to help researchers reexamine important periods in Greek history. In one case, Ithaca confirmed new evidence presented by historians about the dating of a series of important Greek decrees(法令). The decrees were first thought to have been written before 446/445 BCE. But the new evidence suggested a date in the 420s BCE. Ithaca predicted a date of 421 BCE. The date change may seem small but it has significant implications for our understanding of the political history of Classical Athens.
The team is currently working on other versions of Ithaca trained on other ancient languages. DeepMind has launched a free, interactive tool based on the system for use by researchers, educators, museum workers and the public.