Needless to say, deciphering an ancient language when there’s no one left alive who speaks it can be rather daunting. But historical linguists may soon get a helping hand thanks to an AI-based system developed by researchers at MIT.
A team of researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) recently achieved a breakthrough in their efforts to decipher long lost ancient languages by creating an AI-based algorithm that can automatically perform the task, without requiring advanced knowledge of how it relates to other languages.
To create the system, the researchers developed a “decipherment algorithm” and taught it several principles about how languages tend to change over time, grounded in insights from historical linguists.
As a result, the algorithm can categorize words in an ancient language and link them to the equivalents in other related languages. In other words, while it’s not quite capable of acting as a Google Translate to decipher ancient texts into English, it can identify the roots of ancient tongues, explains Futurism.
Ultimately, the goal is to use the system to decipher lost languages that have eluded linguists for decades, using just a few thousand words.
