untitled.gif welcome towards my cool internet house site

[ back | refresh | last 25 | post new ]

welcome to my cool internet home sit is prosecÇ–tedt to a jam

VALID X M L
Hair Cares Product!!!!!
TERRIBLE DISCOVETY!!!!!!!!!!!!!!!!!!!!!!!!!!1!
[11747] by "FARINA00" (ppp-141-10.30-151.libero.it)   on Fri 10 May 2002 09:44:20     reply ] 
FLEE FROM YOUR HOUSE AT ONCE BECAUSE

MOM = [M]ASTER [O]F [M]ANY !!!!!!!!!
all i have 2 say is
[11738] by "UNTOBOT" (user-112025l.dsl.mindspring.com)   on Fri 10 May 2002 01:17:45     reply ] 
not a new product

not
in this day and age of hyper
[11732] by "ENORMOUSmax" (208-58-249-151.s151.tnt1.nwhv.ct)   on Thu 09 May 2002 23:06:04     reply ] 
guys i was just wondering what u think of the Human Condition i.e. what is it? and why? truly


not that i care or anyth
dr. proxy is now a nonja
[11672] by "USA NINJA" (pool-138-88-114-102.res.east.ver)   on Thu 09 May 2002 21:13:54     reply ] 
ARRRRGGGGHHHH!!!!


max tells me every1 wants to oppose!!!!me


and max also opposes me!!!!!!!


I CHALLENGE EVERYONE HERE TO ULTIMATE BATTLE@!!!!!!!!

ps i may or may not have posted this several times, but if i did, it was for EMPHASIZE, not confuse

every1 is challeng'd
whoa1111111
[11653] by "UNTOBOT" (user-112025l.dsl.mindspring.com)   on Thu 09 May 2002 21:05:34     reply ] 

EVERYBOD IS HERE!!!!!
LOOKS LIKE A PARTY!!!!!!!!!
CrapPaper
[11619] by "ENORMOUSmax" (208-58-249-151.s151.tnt1.nwhv.ct)   on Thu 09 May 2002 20:41:18     reply ] 
tobot u have inspired me!!!! here is a non-piss excremnt from my term paper!!! on Ginger Man by Flannel O'Brain

"...[This] passage exposes the reason for the book's title, that Dangerfield is like the mythical sweet cookie; unable to be caught."
i am disguized as dr. proxy soree
[11600] by "pretend 2b dr. proxy" (proxy3a.lmco.com)   on Thu 09 May 2002 14:33:57     reply ] 
i, dr. proxy, would like to ask if Rational Rose will help me write Objectivist Oriented Software

truly yours,
dr. proxy (not a reel doc)
cool
[11595] by "MUCHBETTERTOBOT" (user-112025l.dsl.mindspring.com)   on Thu 09 May 2002 00:51:51     reply ] 

http://www.cnn.com/2002/WORLD/europe/05/08/ireland.priest/index.html

cool i want 2 be excommunicate 2

only that every body nows ,, gi jesus is the son of g
so sad 2 not be dr. proxy o here is webcomic u shold exam
[11571] by "not dr.proxy so sad" (proxy3a.lmco.com)   on Wed 08 May 2002 10:16:28     reply ] 
hi i'm not dr. proxy

just plane ole proxy

neway, u may like

hypocracy.org

a new daily comic by a former cmu member who followed me 2 dr. lockmo's industries. sorry, i mean just plane ole lockmo's industries. the new comic is best viewed with lynx

so sad that im nt reely dr. proxy
Uhm....
[11568] by "DEVELOP00" (ppp-145-35.30-151.libero.it)   on Wed 08 May 2002 05:28:43     reply ] 
....no broken english for once, since I must ask you advice again, mr. Tobot!
Well, maybe someone else could help me too, on the board. Let me explain.

As you know, I developed this program which reads sentences and stores information on what it reads in this form:

[LIST]: all the words I "Learnt"

for each word:
[NEXT 0]
[NEXT 1]
[......]
[NEXT N]

N lists each one containing a list
of pointers to the words following
the root word, at various depths.
For example

THE -> [0] TORUS, AMEBA, PAPER
[1] IS, HAS
[2] STRONG, DEEP, LARGE,SMALL

And so on.

From this multiple chains I can assemble statistically coherent sentences by chaining each word with another one, checking dependencies etc.

Now, I want to add the ability to ANSWER questions, so instead of simple sentences I can feed the program some QUESTION/ANSWER couples of strings and make it learn how some words are related to others.

Of course this implies adding some structures. In a test I made, I added "Groups". In the Groups, each triplet of significant words from the QUESTION (>2 characters in lenghts) was linked to all the words from ANSWER.
Then I searched in the questions that were asked, for the triplets, gave a "frequency bonus" to those words, and so on. It occasionally worked.

Do you have better ideas? Suggestions?
Danke.
home | prev 10 | next 10 ]