MIT Professor Regina Barzilay and MIT PhD student Jiaming Luo recently made a major development in the study of the linguistics of lost languages. They have developed a new system that has been shown to be able to automatically decipher a lost language, without needing advanced knowledge of its relation to other languages.
Working at the Computer Science and Artificial Intelligence Laboratory (CSAIL), Barzilay and MIT PhD student Jiaming Luo developed a decipherment algorithm to track the possible transformations of languages based on findings that suggest that languages generally only evolve in certain predictable ways.
Lost languages reveal the people who spoke them
Recent research suggests that most languages that have ever existed are no longer spoken. Without knowledge or understanding of these languages, we lose all insight into the peoples who spoke them.
It comes even more complicated because some of these dead languages don’t have an apparent relative in any language, and so can’t be compared to any languages we know of. This makes them especially difficult to interpret.
The future of lost languages
This development follows on from a paper Barzilay and Luo wrote last year that successfully decoded the dead languages of Ugaritic and Linear B – even though Linear B had taken researchers decades to decipher.
Their future work involves identifying semantic meaning of the words, even if they don’t know how to read them. The project was partly supported by the Intelligence Advanced Research Projects Activity (IARPA).
Please Support us on Patreon!
Moreover, starting with the pledge level of $3, you will get a digitized vintage book about bookbinding, book history, or book arts each month from us!
These pledges help iBookBinding to continue its work and bring more information about bookbinding and book arts to you!