Research Engineers and Scientists from MIT and Google’s AI lab (Google Brain) are developing ‘machine-learning systems capable of deciphering lost languages’.
”In just a few years, the study of linguistics has been revolutionized by the availability of huge annotated databases, and techniques for getting machines to learn from them…
The big idea behind machine translation is the understanding that words are related to each other in similar ways, regardless of the language involved.”
[Those with sufficient familiarity of crossword puzzles may have recognized a certain ’gestalten’ relationship among certain word groupings.]
”…the process begins by mapping out these relations for a specific language…A machine then searches this text to see how often each word appears next to every other word. This pattern of appearances is a unique signature that defines the word in a multidimensional parameter space…the word can be thought of as a vector within this space. And this vector acts as a powerful constraint on how the word can appear in any translation…”
These scientists are expanding their research to include the decipherment of “lost languages”, possibly even linguists’ ‘Holy Grail’, the ancient Minoan script ‘Linear A’.
Source: Machine learning has been used to automatically translate long-lost languages - Emerging Technology from the arXiv, 1JUL19.
Resource: Neural Decipherment via Minimum-Cost Flow: from Ugaritic to Linear B – Luo, Cao and Barzilay, 16JUN19.
“Quis custodiet ipsos custodes?“ - Decimus Junius Juvenalis
“Numero, Pondere et Mensura“
|Machine Learning <> Lost Language Translation||638||Dr. Troglodyte||02-Jul-19 00:23|
|Re: Machine Learning <> Lost Language Translation||78||Lost_In_Place||02-Jul-19 01:05|
|Re: Machine Learning <> Lost Language Translation||118||cladking||03-Jul-19 04:04|