Translating lost languages using machine learning

by David Solomonoff

MIT researchers have created a machine learning system that aims to help linguists decipher lost languages; System relies on principles grounded in insights from historical linguistics,  captures pertinent patterns of language change and expresses them as computational constraints. Resulting model can segment words in an ancient language and map them to counterparts in a related language.

Source: Translating lost languages using machine learning | MIT News | Massachusetts Institute of Technology

 

Leave a Comment

%d bloggers like this: