|
|
|
|
|
|
by eigenform
1205 days ago
|
|
|
I'm not experienced/well-read in either ML or CT, but awhile ago I remember hearing Tai-Danae Bradley equate "knowing a word by the company it keeps" to the Yoneda lemma, and I always thought that was kind of interesting (although I guess I'm not qualified enough to know whether that statement is useful or vacuous) |
|
|
I'm still shocked no one has developed language learning software along these lines. I had a prototype in the works for thai years ago but never got time to get it off the ground. using statistical models trained on web corpus for a language learning app seems like a no brainer.
think of it like navigating a word as a point in a graph connected to every example context it is in, with associated words being clickable into similar context bundles. then make it differential between host and target language given a translation so you can see which contexts the translation fails and succeeds in.