Folha: AI helps scientists decipher dead languages
Reproduction of Marcelo Viana's column in Folha de S. Paulo.
Around 2300 BC, the conquests of King Sargon the Great made Akkad the first empire in history. The Akkadians adapted the cuneiform script invented by their southern neighbors, the Sumerians, to their language, and admired it: centuries after the Sumerian people had ceased to exist, Akkadian monarchs still styled themselves "kings of Sumer and Akkad".
Akkadian split into Assyrian and Babylonian dialects, which, in the first millennium BC, were replaced by Aramaic and fell into oblivion. But these peoples bequeathed us their texts, written on numerous clay tablets, from which it was possible, in the 19th century, to decipher their languages that had been dead for millennia.
Read more: Ardila cites Brazilian composers at the 2nd CBM plenary session
Maria Soledad presents a lecture on optimal control.
Colloquium promotes debate on women in science.
But reading these texts is difficult and time-consuming. Many clay tablets are damaged or broken. And cuneiform writing is complex: the same symbol can have different meanings depending on the context. If translation between modern languages already requires knowledge of the respective cultures, imagine the difficulty with languages of civilizations that became extinct so long ago. There are few qualified specialists and, therefore, most Mesopotamian texts have never been read.
In a study published in March of this year in the journal PNAS Nexus and on the GitHub digital platform, researchers from Israel and Germany presented anartificial intelligence algorithm that uses convolutional neural networks, a technology similar to that of the popular Google Translate , to translate from Akkadian to English almost instantly.
