A team of scientists from the Massachusetts Institute of Technology have developed a new computer program that could possibly unlock the secrets of ancient texts that are no longer understood, according to the National Geographic (see http://news.nationalgeographic.com).
Working on nothing more than a powerful laptop, the program successfully translated written Ugaritic which was last used around 1200 B.C. in Syria. Ugartic consists of dots and wedge-shaped stylus marks and was first rediscovered in 1928 by archaeologists. It took language experts four years to decode the language and since then it has provided valuable insight into ancient Israelite culture and Biblical texts.
Hebrew is very similar to Ugaritic, and the program managed to connect the Ugaritic symbols to their Hebrew equivalents in less than half a day.
Computers have traditionally been disregarded as effective translating tools for dead scripts since they lack the necessary intuition. This team of scientists from Massachusetts is trying to prove that they can indeed play an useful role.
"Traditionally, decipherment has been viewed as a sort of scholarly detective game, and computers weren't thought to be of much use," wrote study co-author and MIT computer science professor Regina Barzilay.
"Our aim is to bring to bear the full power of modern machine learning and statistics to this problem."
However, critics have voiced doubt over the true effectiveness of this program.
"In the case [of Ugaritic], you're dealing with a small and simple writing system, and there are closely related languages," noted Richard Sproat, an Oregon Health and Science University computational linguist who was not involved in the new work. It's not always going to be the case that there are closely related languages that one can use."
It does seem impossible for the program to translate a dead language that is completely unrelated to other languages we know anything about. Notably, this program translated symbols more than it did language itself and was entirely dependent on the Hebrew ‘sister’ script for reference. Nonetheless, Barzilay believes the decoding program can overcome this hurdle by scanning multiple languages at once and taking contextual information into account — improvements that could uncover unexpected similarities or links to known languages.