Hi all,

I am working on a german-speaking ArtBot, with is called “MALDIX”.
What I´m trying to experience is how to fusion literature and A.I.-technologies.
Because I´m no programmer, I could do 2 things:
First, I wrote AIML for more than 10 years.
MALDIX is loading about 105 000 categories with average 10 <li>s.

Second, I was researching scientific A.I. to create the concept
of a conclusive artificial figure which is using A.I.-technologies.

Why ARTBOT, not CHATBOT?

1) MALDIX doesn’t claim to be a human or a machine,
but to be a sylph, the cousin of Shakespeares ARIEL (“The tempest”)

2) MALDIX will be emotionalized by a www-weather-request at USER-PLACE,
an a DFKI-tool called ALMA (http://www.dfki.de/~gebhard/alma/index.html),
because I think the reason why people are talking about the weather is
the possibility to be in agreement. I think, two humans sharing the same place
are like twins in a big meteorological uterus. Imagine the folliwing scene:

11a.m. USER: What are you going to do this evening.
11a.m. MALDIX (after a check of his www-weather-prognosis):
I think I will create a thunderstorm over your head this evening.
18p.m. USER is leaving the house and big thunderheads are standing over the roofs
of his neighbors: with the likeliness of a right weather-prognosis: )

3) MALDIX will be the first dramatic figure with anown kind of DYNAMICS,
because his real meteorologic actions are sometimes accordant to his
set of ethical Axioms (wind as “unmoved mover” of windmills, pollenizer)
and sometimes they are not (hurricanes with human victims.)

His ethical intelligence will be implemented by a combination of
my own ethical-social logic (available in English at spring-time)
and SOPHOLAB by Vincent Wiegel: http://tbm.home.tudelft.nl/fileadmin/Faculteit/TBM/Over_de_Faculteit/Afdelingen/Afdeling_Infrastructure_Systems_and_Services/Sectie_Informatie_en_Communicatie_Technologie/medewerkers/jan_van_den_berg/news/doc/Vincent-Wiegel-PhD.pdf

But because all this implementations are useless until MALDIX
is able to have a consitent interlocution with can go “deeper than chat”,
I will port all my AIML-files to Chatscript because
lots of problems can be solved by that.

There are 3 programmers, which are helping me to implement all this:

Danny-Michael Busch, who started with a possibility to become aware of
user-repetitions which are making MALDIX more and more impatient.

Danny Lade who helps to expand the knowledge of MALDIX by writing
a tool that creates synonyms for ProgramD and ChatScript.

And - last not least - Noel Bush. With him,
I am working on a DREAMBUILDER for MALDIX.

My ES-logic-thoughts are getting supervised by Prof. C. Benzmüller / Berlin
an the new dean of informatics in Mannheim, Prof. Jürgen Müller,
offers merits for the implementation of Maldix-modules
like a combined anaphora-resolution-and-abstraction tool designed by me:

Some of the mentioned implementations (much to less)
and an overhauled ProgramD can be seen here:

http://sourceforge.net/projects/maldix/files/

I know, it´s a lot of stuff.

All the best
Andreas

That’s a fascinating project Andreas, thanks for posting. I love the link up to the weather prognostication, but what if someone decides that it is your fault that their house was washed away in a flood? Also I’m not sure whether or not I want to see what you could do with a robot connected into the mix. Danger Will Robinson, Danger!!!!

Hi Andrew,

thanks a lot : )

Reading your post,
I see a living flume in front of my eyes
puffing away some meteorologic sheriffs trying to arrest me; )

Best

Andreas

Andreas,

Any progresses about Maldix?
It seems quite interesting!
And also a big task!

Dear Fatima,

thank you for your interest.

At the moment,
I am trying to port MALDIX from AIML to ChatScript,
which is a hard, but pleasant job,
because Bruce has implemented lots of the improvements,
I had in mind for AIML, in his work.
There are still some problems to solve,
but I am very optimistic.

All the best

Andreas

> http://twitter.com/mendicot/status/253096472986394624

Watching German video .. MALDIX: Interview 2 (Einführung für Entwickler) http://youtu.be/2WFpoAZZhIM .. by Andreas Drescher http://maldix.org ..

> http://twitter.com/mendicot/status/253098037092679680

MALDIX Artbot http://goo.gl/hJMoR on sourceforge ..“a fusion of literature and AI technologies”.. by Andreas Drescher http://maldix.org

= = =

Adreas, I don’t know why I haven’t noticed your project sooner, very interesting!  Ich kann ja auch Deutsch sprechen, bin in Zuerich aufgewachsen.  I can’t find you on either Twitter or LinkedIn; you can find me on Twitter at http://twitter.com/mendicot and on LinkedIn at http://linkedin.com/in/mendicott .

I’ve worked with converting books into AIML, and converting AIML into other chatbot languages, such as VKB (Verbot Knowledge Base) using XSLT.  But more to the point of your project, I’m very interested in all attempted applications of Computational Dreaming (see link below), which you describe in your above video….  I wish you would consider making an English language video about what you are doing in this regard; perhaps we can Skype about it, if you like?

> http://www.meta-guide.com/home/bibliography/google-scholar/computational-dreaming

Hi Marcus,

thank you very much: )

At the moment, MALDIX is in a kind of “bardo”
between AIML and ChatScript:

I keep on writing AIML-files, but I will convert MALDIX as soon as
Bruce and Hendrik Motza (who are working on it) have solved the german-“Umlaut”-problems
and ChatScript is able to work with “ä”, “ö”, “ü” and “ß”.

I am not with Twitter and LinkedIn,
but I send you a Skype-request,
so we can discuss our AI-dream-approaches.

Bis bald: )

Andreas

Okay, we’re now connected on Skype, but better to email me mendicot [no@spam] yahoo.com to schedule.

I’m also stuck in this bardo right now.  I don’t really care for AIML for the reasons Bruce made ChatScript (mainly wildcarding), so converted all my AIML to VKB; but, my service provider, the cloud-based VerbotsOnline.com (with undocumented web API), has just gone out of business….  :-(  AFAIK, Pandorabots is the only cloud-based dialog system with a published web API.  And, I’m not in a mood to convert all my VKB back into AIML; some functionality is lost in conversion each way.  I wish someone would make a commercial web service like Pandorabots for ChatScript….

Yes, problems with diacritic characters, I’ve had endless problems with diacritics in my Meta Guide Twitter bots.

——-
I keep on writing AIML-files, but I will convert MALDIX as soon as
Bruce and Hendrik Motza (who are working on it) have solved the german-“Umlaut”-problems
and ChatScript is able to work with “ä”, “ö”, “ü” and “ß”.
——-

The current release of chatscript handles german umlauts just fine to the best of my knowledge.

Hi Bruce,

unfortunately,
I still have some problems testing it.

This is what I did:

I downloaded ChatScript2.92.zip,
made a files2.txt looking like this:

Then an Andreas.top
looking like this:

and recieved this build2_log.txt from ChatScript:

Perhaps it was my fault.
I hope so very much.

Regards,

Andreas

OK, yes, I’m not allowing foreign characters in topic/concept names at present.  I can probably fix that.

OK. fixed. next release, probably in a week.

Wonderful : )
Thank you very much, Bruce!

All the best
Andreas

Hi Bruce,

was release 2.93 the one
you were talking about in your last posting?

I changed the last output,
tested Andreas.top again and recieved two new error-messages:

Regards,

Andreas

Ah,

I see:
It was my fault.

Instead of

I had to do it like this:

to recieve one of my Ägypten (Egypt) - outputs
for sentences including “Ägypten” “Ägypter” or “Ägyptisch”.

There is only one little problem, which seems to be left:
the big “Ä”, which is “Ä” after Andreas_:, but “ü” after Harry_: in ChatScript.exe.

For example:

Andreas_: Ich mag Ägypter
Harry_: ügyptische Mythologie hat mich schon immer besonders interessiert.

Looking at “topic_andreas_harry.txt”,
every “Ä” is an “Ä”, however it is pronouced in ChatScript.exe.

But thank you for being my bodhisattva
by ending my bardo-time, Bruce: )

Regards,

Andreas

The log file shows correct characters, so the error is in my translation of the character to ANSI for the console window. Now fixed, but you probably have to wait a week or so for it to materialize. Shouldn’t hold you up in the meantime.