On 2/27/2013 5:37 PM, Obrst, Leo J. wrote:
> Anyone who uses Eliza-based NLP templates, I say: pity the fools. (01)
An "Eliza-based template" is a regular expression. Such expressions
have been widely used for searching and information extraction for
decades. (02)
But Eliza had more than just a set of templates. Each template
was used as a pattern that would be matched to the current input
stream and would trigger some rule. In effect, Eliza implemented
production rules with just one-step forward chaining. (03)
Later Eliza-like systems used production rules that allowed
multiple-step forward chaining *and* the option of a "context"
switch. Each context had its own set of patterns and rules.
The set of contexts and the rules that made transitions from one
context to another could be represented by a finite-state machine. (04)
The above two paragraphs are the basis for many, if not most
of the annoying phone answering systems you get when you call
an airline, a bank, or any company from which you would like
some useful service. (05)
I agree that they are annoying, and they're not state of the
art in NLP. But at least they're a step up from the useless
help facilities based on keywords. (06)
John (07)
_________________________________________________________________
Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
Config Subscr: http://ontolog.cim3.net/mailman/listinfo/ontolog-forum/
Unsubscribe: mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
Shared Files: http://ontolog.cim3.net/file/
Community Wiki: http://ontolog.cim3.net/wiki/
To join: http://ontolog.cim3.net/cgi-bin/wiki.pl?WikiHomePage#nid1J (08)
|