gawkinet: Challenges
2.12 Where To Go From Here
==========================
Now, you have learned enough to build your own application. You could,
for example, take part in the Loebner Contest to win $100,000. The
Loebner Prize is the first formal instantiation of a Turing Test. Hugh
Loebner agreed with The Cambridge Center for Behavioral Studies to
underwrite a contest designed to implement the Turing Test. Dr. Loebner
pledged a Grand Prize of $100,000 for the first computer whose responses
were indistinguishable from a human's. Each year an annual prize of
$2000 and a bronze medal is awarded to the _most_ human computer. The
winner of the annual contest is the best entry relative to other entries
that year, irrespective of how good it is in an absolute sense. Here is
an example of a conversation with the winning program of 1997:
(c)1997 Cambridge Center For Behavioral Studies all rights reserved [CONVERSE]
[Intelligent Research Ltd.] Start at: [1997/04/29 08:59:40]
PROGRAM[10:39:20]Hi, my name is Catherine, what's yours?
JUDGE02[10:39:36]My name is Nathan.
PROGRAM[10:39:37]Well, it's nice to meet you, Nathan.
PROGRAM[10:39:45]Did you see that story on CNN last night about the lesbian
PROGRAM[10:40:03]couple who came out at a White House party on Sunday?
JUDGE02[10:40:45]No. I'm sorry I missed that. How did the Prez take it?
PROGRAM[10:40:47]Ellen Degeneres was one of them - she was kissing her lover
PROGRAM[10:41:08]in front of Bill Clinton. Do you think he was very
PROGRAM[10:41:21]embarrassed?
JUDGE02[10:41:37]You tell me. I didn't see it.
PROGRAM[10:41:38]Are you still a Friend of Bill Clinton?
JUDGE02[10:42:22]Yes. I would like to talk about something else. Do you know anything about sculpture.
PROGRAM[10:42:24]Well, I suppose he's doing his best like most of us, but he
PROGRAM[10:42:35]does seem to attract an UNUSUAL amount of bad publicity,
PROGRAM[10:42:51]wouldnt you say--can it all be bad luck?
JUDGE02[10:43:20]I asked you if you knew anything about sculpture.
PROGRAM[10:43:21]OK, but what happens now--does it all drift on, with
PROGRAM[10:43:36]everyone waiting to see how much his friends have said about
PROGRAM[10:43:47]him under threat of lots and lots of jail-or will something
PROGRAM[10:44:01]dramatic actually happen?
JUDGE02[10:44:19]Do you know what sculpture is?
PROGRAM[10:44:20]Well, youre more a fan of his than I am I guess---though I
PROGRAM[10:44:34]cant SWEAR what Id have done in that locked hotel room, I
PROGRAM[10:44:51]must say.
JUDGE02[10:45:26]Have you ever been to the Salmagundi Club?
PROGRAM[10:45:29]Never. to go back to the original discussion Time to get
PROGRAM[10:45:43]off this one I think and onto something more down to earth!
JUDGE02[10:46:20]What is more down to earth than art?
PROGRAM[10:46:21]I don't know what -- to be honest. -
PROGRAM[10:46:30]I suppose it depends on where you're coming from, but as the
PROGRAM[10:46:46]song goes in My Fair Lady, "Why can't a woman be more like a
PROGRAM[10:47:03]man? "
JUDGE02[10:47:52]I liked that song but I prefer "Why can't children be more like we are"
JUDGE02[10:48:10]from another play the name of which I cannot remember.
PROGRAM[10:48:12]What, if anything, do you enjoy about being a man?
JUDGE02[10:49:01]I would enjoy all aspects of life no matter what my gender.
PROGRAM[10:49:02]Do you think of yourself as being attractive?
This program insists on always speaking about the same story around
Bill Clinton. You see, even a program with a rather narrow mind can
behave so much like a human being that it can win this prize. It is
quite common to let these programs talk to each other via network
connections. But during the competition itself, the program and its
computer have to be present at the place the competition is held. We
all would love to see a 'gawk' program win in such an event. Maybe it
is up to you to accomplish this?
Some other ideas for useful networked applications:
* Read the file 'doc/awkforai.txt' in the 'gawk' distribution. It
was written by Ronald P. Loui (at the time, Associate Professor of
Computer Science, at Washington University in St. Louis,
<loui@ai.wustl.edu>) and summarizes why he taught 'gawk' to
students of Artificial Intelligence. Here are some passages from
the text:
The GAWK manual can be consumed in a single lab session and
the language can be mastered by the next morning by the
average student. GAWK's automatic initialization, implicit
coercion, I/O support and lack of pointers forgive many of the
mistakes that young programmers are likely to make. Those who
have seen C but not mastered it are happy to see that GAWK
retains some of the same sensibilities while adding what must
be regarded as spoonsful of syntactic sugar.
...
There are further simple answers. Probably the best is the
fact that increasingly, undergraduate AI programming is
involving the Web. Oren Etzioni (University of Washington,
Seattle) has for a while been arguing that the "softbot" is
replacing the mechanical engineers' robot as the most
glamorous AI testbed. If the artifact whose behavior needs to
be controlled in an intelligent way is the software agent,
then a language that is well-suited to controlling the
software environment is the appropriate language. That would
imply a scripting language. If the robot is KAREL, then the
right language is "turn left; turn right." If the robot is
Netscape, then the right language is something that can
generate 'netscape -remote
'openURL(http://cs.wustl.edu/~loui)'' with elan.
...
AI programming requires high-level thinking. There have
always been a few gifted programmers who can write high-level
programs in assembly language. Most however need the ambient
abstraction to have a higher floor.
...
Second, inference is merely the expansion of notation. No
matter whether the logic that underlies an AI program is
fuzzy, probabilistic, deontic, defeasible, or deductive, the
logic merely defines how strings can be transformed into other
strings. A language that provides the best support for string
processing in the end provides the best support for logic, for
the exploration of various logics, and for most forms of
symbolic processing that AI might choose to call "reasoning"
instead of "logic." The implication is that PROLOG, which
saves the AI programmer from having to write a unifier, saves
perhaps two dozen lines of GAWK code at the expense of
strongly biasing the logic and representational expressiveness
of any approach.
Now that 'gawk' itself can connect to the Internet, it should be
obvious that it is suitable for writing intelligent web agents.
* 'awk' is strong at pattern recognition and string processing. So,
it is well suited to the classic problem of language translation.
A first try could be a program that knows the 100 most frequent
English words and their counterparts in German or French. The
service could be implemented by regularly reading email with the
program above, replacing each word by its translation and sending
the translation back via SMTP. Users would send English email to
their translation service and get back a translated email message
in return. As soon as this works, more effort can be spent on a
real translation program.
* Another dialogue-oriented application (on the verge of ridicule) is
the email "support service." Troubled customers write an email to
an automatic 'gawk' service that reads the email. It looks for
keywords in the mail and assembles a reply email accordingly. By
carefully investigating the email header, and repeating these
keywords through the reply email, it is rather simple to give the
customer a feeling that someone cares. Ideally, such a service
would search a database of previous cases for solutions. If none
exists, the database could, for example, consist of all the
newsgroups, mailing lists and FAQs on the Internet.
Info Catalog
gawkinet: Caveats
gawkinet: Using Networking