A project led by professor Regina Barzilay of the Massachusetts Institute of Technology may be the first to show how ancient, lost or unknown languages can be decoded using a computer program, according to National Geographic.
The MIT team was able to decode the "lost language" of Ugaritic, an ancient Semitic language used in Old Testament times, using no more computing power than that of a laptop. The program took no longer than a few hours to link most Ugaritic symbols to their Hebrew equivalents.
Ugaritic text was nothing more than a series of dots and wedge-shaped marks to linguists and scholars when it was first discovered on clay tablets in 1928, excavated from the rubble of the ancient city of Ugarit by French archaeologists. Even though the language is closely related to Hebrew, experts did not decipher it until 1932.
It took only hours to accomplish what took linguists years to complete, leading scholars to hope that the new computer program can be a prototype for a more powerful system to decode ancient languages that remain a mystery to scholars. In other words, it may not be long before computers become modern day versions of the Rosetta Stone.
"Traditionally, decipherment has been viewed as a sort of scholarly detective game, and computers weren't thought to be of much use," Barzilay said. "Our aim is to bring to bear the full power of modern machine learning and statistics to this problem."
But some experts remain skeptical. Richard Sproat, an Oregon Health and Science University computational linguist, notes that "in the case [of Ugaritic], you're dealing with a small and simple writing system, and there are closely related languages. It's not always going to be the case that there are closely related languages that one can use."
For example, a language like Etruscan, which was used by ancient Italians around 700 B.C., is known today from scant written examples and shares no relation to any other known language, except for a few words adopted by the Latin language (e.g., the name of the city of Rome comes from Etruscan). Deciphering Etruscan symbols could potentially give historians invaluable contextual clues about the region before Latin superseded the earlier language.
Barzilay thinks the MIT program can be upgraded to decode languages like Etruscan by scanning multiple languages at once and taking contextual information into account. At the very least, such a program could reveal new, obscure clues that scholars can use to learn more about ancient unknown languages.