Re:Toddlers’ grammar skills not inherent, but learned, new S...
by stared on Friday February 24, 2017 @06:41AM
(#13722758)
See also: On Chomsky and the Two Cultures of Statistical Learning by Peter Norvig: http://norvig.com/chomsky.html
[ Parent
| on HN ]
Re:Toddlers’ grammar skills not inherent, but learned, new S...
by lngnmn on Friday February 24, 2017 @02:04PM
(#13726598)
This basically postulates that language learned is a process similar to a supervised machine learning algorithms, and this, perhaps, is a more realistic view that Chomsky has. The machinery has been evolved, but "the training data" is required to make it work.
Re:Toddlers’ grammar skills not inherent, but learned, new S...
by ubernostrum on Friday February 24, 2017 @11:13PM
(#13730004)
Be careful of the trap: for quite a while now, each generation has simply treated it as "realistic" to match the brain's workings to that generation's popular new computational technique.
Re:Toddlers’ grammar skills not inherent, but learned, new S...
by neutralid on Friday February 24, 2017 @02:31PM
(#13726878)
What's interesting is that Google's Translate, via neural network training, seems to have found an efficient structure underlying many languages:
https://www.newscientist.com/article/2114748-google-translat...