Ben Goertzel wrote:
No, the mainstream method of extracting knowledge from text (other
than manually) is to ignore word order. In artificial languages,
you have to parse a sentence before you can understand it. In
natural language, you have to understand the sentence before you
can parse it.
More exactly: in natural language, you have to understand the sentence
before you can disambiguate amongst the roughly 1-50
(syntactically-correct-but-not-necessarily-meaningful) parses that
contemporary parsers provide.
-- Ben
I don't know. People don't fully understand most of what they read. They
just understand enough for their own purposes.
And a lot of what they do understand is: the motives of the person
communicating in communicating what they do. People would never
communicate if they didn't have some (self-beneficial) purpose to do so.
And this is a lens we always look through in interpreting information
coming from some source. Managing the purposes others see in our own
communication -- is also an important component in how humans communicate.
Also, human communication comes in bite-sized chunks. Because humans
would not be able to understand an extremely long sentence that might
(to someone who could understand it) communicate more accurately. We
have to set up an idea -- frame it -- before we introduce new concepts
or new scopes and views of the information. Thus the concept of a
Main-Idea-Sentence in a paragraph.
- Dimitry
____________________________________________________________
Save on Emergency Alert Systems. Click here.
http://thirdpartyoffers.juno.com/TGL2141/fc/Ioyw6i3mXtacqvG9l7cxMDI9HIpEjLtcD22CuZMOjXGPI1ZH1DkRWf/
-------------------------------------------
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=114414975-3c8e69
Powered by Listbox: http://www.listbox.com
