...life can be translucent

Menu

Data storage in the Chinese character

yly2pg1

visitor
Joined
Dec 29, 1972
Messages
830
Reaction score
0
http://www.news.cornell.edu/stories/Aug05/comp.learns.language.ssl.html

Quote:
<font size="-2">"The algorithm -- the computational method -- for language learning and processing that we have developed can take a body of text, abstract from it a collection of recurring patterns or rules and then generate new material," explained Shimon Edelman, a computer scientist who is a professor of psychology at Cornell and co-author of a new paper, "Unsupervised Learning of Natural Languages," published in the Proceedings of the National Academy of Sciences (PNAS, Vol. 102, No. 33).

"This is the first time an unsupervised algorithm is shown capable of learning complex syntax, generating grammatical new sentences and proving useful in other fields that call for structure discovery from raw data, such as bioinformatics," he said.

Unlike previous attempts at developing computer algorithms for language learning, the new method, called Automatic Distillation of Structure (ADIOS), successfully identifies complex patterns in raw texts. The algorithm discovers the patterns by repeatedly aligning sentences and looking for overlapping parts.</font>
 

lightofdarkness

visitor
Joined
Mar 16, 1970
Messages
1,025
Reaction score
0
ADIOS - "recursively distills from it hierarchically structured patterns"

Using such a method is using what IDM shows - that basic meaning is derived from recursive processes and the hierarchy reflects the movement from general to particular, from semantics to syntax. REPRESENTATIONS of that meaning is in the form of letters/words etc and so can be detected.

What they most likely have NOT yet come across is the XOR material that comes out of recursing categories.
 

yly2pg1

visitor
Joined
Dec 29, 1972
Messages
830
Reaction score
0
in that case, it is not a bad idea for you to contact Zach Solan ...
 

Clarity,
Office 17622,
PO Box 6945,
London.
W1A 6US
United Kingdom

Phone/ Voicemail:
+44 (0)20 3287 3053 (UK)
+1 (561) 459-4758 (US).

Top