paper.txt

megahal is the conversation simulators conversing with a user in natural language. The program will

* Read the user's input, and segment it into an alternating sequence of
  words and non-words.

* From this sequence, find an array of keywords and use it to generate
  many candidate replies.

* Display the reply with the highest information to the user.

* Use the user's input to update the Markov models, so that MegaHAL can
  learn from what the user types.

This sequence of steps is repeated indefinitely, which allows the program
to learn new words, and sequences of words, as it converses with the user.

4.4 Training MegaHAL

When MegaHAL is started it has no knowledge of language, and is unable to
give a reply at all---the program needs to be trained using a source of
text to ensure that it does not reveal its identity prematurely.  A large
corpus of training data was created for this purpose.

The training data is made up of various texts:

* Hand-crafted sentences designed in order to create a personality for
  MegaHAL, including sentences containing a false name, age and occupation.

* Encyclopaedic information taken from the Web, on topics such as
  geography, music, sports, movies and history.

* A selection of sentences picked from transcripts of previous Loebner
  contests.

* Lines of dialogue taken from scripts for movies and television shows.

* Lists of popular quotations.

* A small amount of text in languages other than English.

When MegaHAL is trained using this data, it is able to respond to questions
on a variety of topics.  It is hoped that the program will also learn new
topics from the judges, although this remains to be seen.

4.5 Online Experimentation

MegaHAL has been available on the Web since early in 1997, and hundreds of
users converse with it every day.  It is an interesting fact that one never
tires of reading transcripts of conversation, due to MegaHAL's ability to
respond with original replies.

Many users are often offended by the things MegaHAL says, and some believe
that they have been personally insulted.  One user, named Forrest, was
quite incensed when the program began quoting parts of the Forrest Gump
screenplay back at him.  That a computer program can cause such an
emotional response in a human being is interesting, although it may say
more about the human being than it does about the program.

Users are often impressed with MegaHAL's ability to learn.  One user was
annoyed that the program had learned more about his personal life than he
would care it to know, while another stated that MegaHAL would eventually
grow into a person of average intellect (he attributed this bold claim to
the law of averages).  One user, experienced working with people in
psychotic crises, likened talking to MegaHAL with talking to a psychotic.

Users have succesfully taught the program to respond to sentences in
French, Spanish, Greek, German, Italian, Latin, Jananese and Hebrew,
amongst others.  A clergyman spent hours teaching MegaHAL about the love
of Jesus, only to constantly receive blasphemous responses.

The reaction of Web user's to the program has been surprising, and is
pretty much what Weizenbaum experiences with ELIZA.  MegaHAL generates
gibberish mostly, but occasionally, by pure coincidence, it will come out
with an appropriate response.  It is these occasions that stick in the
mind, and give cause for over-zealous claims of computational intelligence.

4.6 Example Interaction

As an example of MegaHAL at its best, we give here a few extracts from
a conversation which took place, over a period of three hours in mid 1997,
between MegaHAL and an anonymous Web user.

To begin with, the user was able to successfully teach the program
some basic facts:

   User:    Roentgen discovered the X-rays.
   MegaHAL: THE NOBEL PRIZE FOR PHYSICS IN 1900 WAS WON BY ROENTGEN.
   User:    Who discovered the X-rays?
   MegaHAL: ROENTGEN DISCOVERED THE X-RAYS.

He then discovered that the program is an expert an being nonsensical.
Even so, MegaHAL was still able to give some appropriate responses, due to
the keyword mechanism for generating replies:

   MegaHAL: WHEN WE BEGIN TO RESOLVE SOME OF MY THUMBS, SOMETHING
            WICKED THIS WAY COMES
   User:    what is the meaning of your last assertion ?
   MegaHAL: HAVE YOU LEARNED SINCE WE LAST SPOKE?
   User:    I've learned I'm not experienced enough to modelize your
            brain system
   MegaHAL: YOU'VE FINALLY CONFUSED ME.
   User:    I've learned nothing
   MegaHAL: HAVE YOU LEARNED ANYTHING ABOUT INSANITY?
   User:    are you stupid
   MegaHAL: I AM NOT STUPID! REALLY!

Finally, the user discovered that the program could respond in other
languages:

   User:    Tu parles francais?
   MegaHAL: I GUESS SO. PARLEZ-VOUS FRANCAIS?
   User:    L'amour est une passion humaine.
   MegaHAL: LA LANGIDOCE EST UNE PETITE JEUNNE FILLE

In general MegaHAL's conversations are not as successful as this.  Most
users are satisfied with typing in rude words to see how the program
responds.



5. Conclusion

MegaHAL uses a technique which differs significantly from that used by
previous entrants to the Loebner contest.  It has been submitted in 1998
for the purpose of demonstrating a different method of simulating
conversation.  Although its replies are occasionally lucid, MegaHAL is most
definitely not an Artificial Intelligence; we must be careful not to read
too much into what it says.

The Loebner contest does offer some benefits (Loebner, 1994); it provides
an annual Turing test for anyone who cares to submit an entry, it promotes
and stimulates interest in the field of Artificial Intelligence, it
encourages competition, it could conceivably result in new techniques which
may be applicable to fields outside of Artificial Intelligence and it
stimulates discussion amongst researchers.  Even so, we believe that the
contest is not advancing the field of Artificial Intelligence because,
although the $2000 is a guaranteed reward, it is not a large enough carrot
to entice serious research groups.

Perhaps the most important contribution of the Loebner contest is the
insight it provides into the psychology of conversation---it makes us aware
of how little our understanding of conversation lies in what is said.



Notes

1. Today the program must also satisfy audio-visual requirements to win the
   grand prize.

2. A symbol refers to both words and non-words.



References

Colby, Kenneth Mark.  1981.  Modeling a paranoid mind.  The Behavioral and
Brain Sciences, 4:515--560.

Epstein, Robert.  1992.  Can machines think?  AI Magazine, Summer:80--95.

Hutchens, Jason L.  1994.  Natural language grammatical inference.
Honour's thesis, University of Western Australia, December 1994.  Available
at: http://ciips.ee.uwa.edu.au/Papers/

Hutchens, Jason L.  1996.  How to pass the turing test by cheating.
Available at: http://ciips.ee.uwa.edu.au/Papers/

Jelinek, Frederick.  1986.  Markov source modeling of text generation.
Technical report, IBM T.J. Watson Research Center.

Loebner, Hugh.  1994.  In response to lessons from a restricted Turing
test.  Available at: http://acm.org/~loebner/In-response.html

Moor, James H.  1976.  An analysis of the turing test.  Philosophical
Studies, 30:249--257.

Shannon, Claude E. and Warren Weaver.  1949.  The Mathematical theory of
Communication.  University of Illinois Press.

Shieber, Stuart M.  1994.  Lessons from a restricted turing test.
Available at the Computation and Language e-print server as cmp-lg/9404002.

Turing, A.M.  1992.  Computing machinery and intelligence.  In D.C. Ince,
editor, Collected works of A.M. Turing: Mechanical Intelligence. Elsevier
Science Publishers, chapter 5, pages 133--160.

Weizenbaum, Joseph.  1976.  Computer Power and Human Reason.  W.H. Freeman
and Company.