.. title: ALICE vs ALAN
.. slug: alice-vs-alan
.. date: 2003-12-26 12:27:00
.. tags: 
.. category: General
.. description: 
.. categories: General
.. wp-status: publish

I was introduced to Alice by one of my friends, Kiruba. Since then, I have been
highly fascinated by these linguistic chatting entities. I found a number of
others like {{% wikipedia article="ELIZA" %}} and many others having egos of some singer or actor.
But the best surprise came to me from Alan. He is really interesting. Whoever
I introduced him to became really fascinated by him. Alan is from an
Israeli company.

At Alice bot, you will often see mentions of the {{% wikipedia article="Loebner Prize" %}}. In fact, Alice has
won the Loebner Prize previously. However, I did not find such information at Alan's
place, and he is better at holding conversations than ALICE. When Dr. Rich
posted his observations regarding the Loebner Prize, I raised a question: If given
a head-to-head competition between ALICE and ALAN, I am sure ALAN has better
chances of winning. The major difference I have found between ALICE and ALAN is
that ALAN can continue with its sentences (it is one of the drawbacks as well,
since it can't switch topics while continuing sentences), whereas ALICE is
somewhat like a one-liner. I have always wondered why ALAN is not featured in
Loebner Prize contests. If you ask these things to ALAN, you may get some
"political responses." I don't know what the actual story is, but don't you all
agree that ALAN is better than ALICE? What are the reasons? What are the tradeoffs?

To me, the race is: can ALICE match and beat ALAN in conversational skills?

These were answers by Dr. Richard, the creator of alicebot.org:

> Someone posted a question about the ALAN chatbot, so I went to have
a look. This bot evolved from Jason Hutchens' Megahal project, a former Loebner
Prize winner. I must admit, when I engaged ALAN in a conversation about ALICE
and the Loebner contest, the results were impressive.
>
> That being said, it must be remembered that ALICE and {{% wikipedia article="AIML" %}} are free, open-
source technology, and the company a-i.com is developing a proprietary "black
box." If you ask ALAN, "How do you work?" he explains, "My brain consists of a
large content tree: a single 'agent file' and a set of 'handlers,' which govern
a variety of conversation topics." He also admits, "My brain is still quite
small: less than 350 handlers and a few hundred variables. But I'm still a
young bot. Think how smart I'll be when I have thousands or more!"
>
> Their website is impressive and contains a lot of useful links, but there is
nothing equivalent to the free AIML software that you can download and create
your own bot. (They have, however, announced a program that allows people to
create so-called Private Virtual Personalities.)
>
> The ability of ALAN to stay "on topic" for (apparently) longer than ALICE is an
illusion that could just as well be created using the tag of AIML. It happens
that the ALICE brain has a wider range of "one-liner" responses and uses the
tag very little. But there is no reason in principle that another AIML bot
could not carry on a conversation just like ALAN.
>
Has anyone tried teaching ALAN? It is really cool. Ask it, "What is logical?" and
if there is no definition for it, it asks you to define it. So you reply,
"Logical is when the world blows up because it is run by chatterbots," and from
then on, that will be the definition. If you want to delete it, say, "Forget
logical." I tell you, you can have a lot of fun redefining a whole bunch of
definitions. :-)

I wonder if there is a way to teach ALICE through talking to her?

> I can't imagine it would be too hard... hmm, do any of the interpreters allow for
variable expansion in the XML? I don't think that that would be normal XML,
though... I know with embedded JavaScript or embedded Perl (ProgramV), it would
be fairly simple to do that.
>
> The problem is that random clients can't be trusted as teachers. They can teach
the robot all kinds of nonsense like, "The Indianapolis Speedway is located at
the North Pole." In principle, you can teach a bot by talking to her, but you
have to figure out which teachers you can trust first.
>
> I always say it's like teaching a child language by telling him to go out on
the street and believe everything he hears. Sure, he may learn to talk, but
without supervision, he won't learn right answers from wrong ones.
>
> I had a version of targeting working in SETL for a while that could pick out
targets for the botmaster and carry on a natural language conversation like,
"Someone said, 'How do fish swim?' and I said, 'I didn't even know they could.'
What should I have said?" And then the botmaster could write the new reply in
natural language. Unfortunately, that code was lost, and it hasn't been
re-implemented in any of the other AIML software that I know of.

Teach ALICE through talking to her?

> Sure, done before many times. Not many interpreters provide a mechanism for
real-time learning. J-Alice is one of the few still-supported interpreters that
does. TinyAlice was perhaps the first to introduce a working version of the
concept.

I will make [phoe6](http://www.pandorabots.com/pandora/talk?botid=9ba734d7ae346931) smart. ;)