Prof. Mark Last (Photo Credit: Dani Machlis/BGU)
Researchers at Israel’s Ben-Gurion University are using artificial intelligence to “rediscover” illegible letters and words in ancient Hebrew and Aramaic inscriptions and texts. Such writings are being uncovered all of the time by archeologists in Israel, and there is also a wealth of ancient writings with faded text to be deciphered. So, such new technology could lead to major breakthroughs in our understanding of the ancient world and of how the Jews lived in the Biblical age.
Every year more ancient texts are discovered in both the Hebrew and Aramaic languages throughout the Near East, explained the Ben Gurion University researchers. The analysis of these texts is “extremely important for researchers studying the culture and history of the region,” they said.
This is a task for epigraphists – detectives of the past, specializing in the fascinating world of inscriptions or epigraphs.
Will you offer us a hand? Every gift, regardless of size, fuels our future.
Your critical contribution enables us to maintain our independence from shareholders or wealthy owners, allowing us to keep up reporting without bias. It means we can continue to make Jewish Business News available to everyone.
You can support us for as little as $1 via PayPal at [email protected].
Thank you.
Epigraphy itself is the study of these inscriptions, and it goes beyond just reading the words. Epigraphists meticulously analyze the inscriptions to decipher their meaning, identify the writing system used, date them, and understand the cultural context in which they were created. Their work is crucial for piecing together history, language development, and everyday life in ancient civilizations.
As many inscriptions are damaged over time due to earthquakes, fires, political conflicts, and other natural and human-related causes, epigraphists encounter a “major challenge in reconstructing the missing parts of these valuable writings.” Until now, they have used time-consuming manual procedures to estimate the missing content.
The Department of Software and Information Systems Engineering students at Ben-Gurion University of the Negev say they have approached this challenge as “extended masked language modeling task where the damaged content can comprise single characters, character n-grams (partial words), single complete words, and multi-word n-grams.”
In their final project under the supervision of Prof. Mark Last, the fourth-year undergraduate students Niv Fono, Harel Moshayof, Eldar Karol, and Itay Asraf applied the masked language modeling approach to corrupted inscriptions in Hebrew and Aramaic. Their model, “Embible,” was highlighted at the latest meeting of the European Chapter of the Association for Computational Linguistics last month.
The students trained the system on 22,144 sentences from the Old Testament. The system was tested on the other 536 sentences with noted success. An ensemble of word and character prediction models had the highest accuracy.
“We can help historians who have devoted their lives to recreating these ancient texts as accurately as possible,” says Prof. Last, “Furthermore, I believe the model can be extended to cover other morphologically rich ancient languages.”
