On Fri, Oct 17, 2008 at 8:17 AM, Matt Mahoney <[EMAIL PROTECTED]> wrote: > Likewise, writing software has to be understood in terms of natural language > learning and modeling. A programming language is a compromise between what > humans can understand and what machines can understand. Humans learn C++ > grammar and semantics by induction, from lots of examples. Machines know C++ > from an explicit specification. > > Natural language is poorly understood, which is exactly why we need to study > it.
I don't disagree, but I think a lot of NLP is done in isolation, with no regard to semantics.. so you get a neat little parsing algorithm but don't really learn anything about what natural language is *for*. I think language has to be about something.. and the human on the other side of the conversation has to actually care about what the AGI has to say, and having the AGI understand what he/she has to say. Because if you don't really care what the AGI does.. just so long as it does something intelligent.. you might as well restrict your language to "good dog", "bad dog" re-enforcement learning. Trent ------------------------------------------- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=117534816-b15a34 Powered by Listbox: http://www.listbox.com
