Marcus L Endicott: Chatbots.org AI Zone


Marcus Endicott, appreciated member of Chatbots.org


Development › My Chatbot Project: Generating traffic – beyond the usual tools

> http://twitter.com/twaveladvisor

Vince, I’ve done a huge amount of work with “socialbots”, so much so that I’m getting too tired of it to review again here. Above, you can see a link to my “Twaveladvisor” on Twitter. It is parsing travel questions off the Twitter firehose, and then running them through the Pandorabots API and returning answers to Twitter. Note that “@” signs are being replaced with “#” hashtags in order to conform to Twitter policies as well as simply respect other Twitter users. In order to unlock this social “gold”, your chatbot will need to be available as an API, which is one reason for my ongoing strong emphasis on dialog system APIs.

> http://www.mendicott.com/2012/06/250-conversational-twitter-bots-for.html

See my blog post on “250 Conversational Twitter Bots for Travel & Tourism”, above.

> http://www.meta-guide.com/home/twitterbots/100-best-twitter-bots

And, check out my Meta Guide webpage, “100 Best Twitter Bots”, at the above link.

= = =

> http://www.meta-guide.com/best-facebook-chatbots

I’ve also got a Meta Guide webpage on “Best Facebook Chatbots”, above.

Historically the Facebook API has been more tightly controlled against socialbots than the Twitter API; however, that is now changing. Twitter is taking drastic measures to lock down its formerly open ecosystem, which are supposed to be completed by March 2013. For this reason, after spending years working with socialbots on Twitter, I’ve decided to throw in the towel (well at least partially), and move on to something else in 2013.

= = =

> http://en.wikipedia.org/wiki/Webring

Steve and Dave’s suggestions remind me of “webrings”. Remember those?

> http://hub.webring.org/hub/talk2mecomputerw

It looks like there’s still a “Chatbot Webring”, but seems to contain only 2 sites.

= = =

> http://books.google.com/ngrams/

According to the Google Books Ngram Viewer, Webrings seemed to have peaked out in 2002 (if not before).

Development › AIML & other standards: Masterlist of AIML Editors

Is there a masterlist of AIML Editors available anywhere?

Has a “history” of AIML Editor development been published anywhere?

I suppose this should include general XML Editors as well; so, what would be your favorites?

I know Adeena Mignogna has done work in this area, and will send her a pointer to this thread.

I’m particularly interested in finding an AIML Editor with convenient CSV export….

= = =

> http://twitter.com/mendicot/status/172306171510788097

According to the Annabot project http://bit.ly/x7rvRe .. Altova @XMLSpy is the best XML editor & XSLT processor for #AIML knowledgebases ..

= = =

> https://www.youtube.com/watch?v=lJuTq5maDl4

Editing Bot Content with a Spreadsheet Editor (Richard Wallace)

> https://www.youtube.com/watch?v=JPtWvB0-3bw

Chatbots 3.1 – Adeena Mignogna – AIML Content Management (1of2)

> https://www.youtube.com/watch?v=I_6f_sGZ0Ig

Chatbots 3.1 – Adeena Mignogna – AIML Content Management (2of2)

= = =

> http://riotsw.com/sae.html

Download Simple AIML Editor (Adeena Mignogna)

= = =

> http://www.ai-dealer.com/AIML-Editor.html

I tried the “Ai-Dealer” AIML Editor by Brian Hoecht, but was not impressed with its “special” functions, so never put it to any real use.

= = =

> http://www.gaitobot.de/

I’ve also tried the GaitoBot AIML Editor, but didn’t find it particularly memorable either.

= = =

Hi Vincent, thanks for the offer. Dave has also kindly offered his help too. At the moment I’m just looking for the most convenient way to convert back and forth between CSV<=>AIML. I thought a review of the AIML Editor options might reveal one with this feature. I’m still trying to marry Mindmaps with AIML, converting both ways, one into the other. I’m neither a database expert nor a PHP expert, though have dabbled in both. I did find Richard Wallace’s recent explanations in the “Jan’s AIML importer” topic encouraging. Let me know if you have any ideas or suggestions!

= = =

> http://www.chatbots.org/ai_zone/viewthread/854/

Alright, this relates to my previous work with sitemaps and bookmarks, see above link. Actually, I believe it’s the XML Bookmark Exchange Language (XBEL) that has the ability to represent nesting. And, according to Richard Wallace’s recent explanations in the “Jan’s AIML importer” topic, AIML follows a “tree” structure, as represented in my XPath HTML5 parser screenshot, also under the above link.

Development › AIML & other standards: Masterlist of AIML Editors

> http://downloads.r-i-software.com/downloads/AIML/aiml_editor.zip

Thanks Vincent! I tried your conversion tool. It doesn’t recognize the *.aiml extension, so just had to rename files to *.xml. I then tried saving as *.csv, before I noticed the “export” option. I tried a number of standard *.aiml files from Pandorabots. Some of the files did not import completely (at least upon export), and some seemed to be confused about the “nesting”. I’m not sure its a good idea to spend a lot of time on this, but does seem to be a very good start.

> http://www.meta-guide.com/github-aiml

= = =

Dave, I knew it could be done using XSLT; I was just looking for an easier, and quicker “manual” proof of concept before automating the processes.

> http://www.meta-guide.com/xml-variants

I started by examining the XML Variants, above.

> http://www.meta-guide.com/mindmap-conversion

Then got deeper into Mindmap Conversion at the above link.

> http://en.wikipedia.org/wiki/Freeplane

Freeplane seems to be more up to date than Freemind. There are lots of mindmap (mm) files available online. I suggest just open a number of those in Freeplane, and then export to code. (I wouldn’t use any of the commercial mindmapping programs, because they tend to contain more proprietary elements than the open source ones.) The “nesting” issue keeps rearing its head. The reason I am focussing on CSV is to better understand how all of the elements relate to one another, to avoid getting lost in nesting “hell”.

To bring this back to the topic at hand, it would be nice to have a *visual* AIML Editor (like mindmaps), and maybe even a collaborative, online editor (perhaps like “DIDO” mentioned up thread). It would also be nice to have an AIML Editor that could import both mindmaps and sitemaps (as well as export CSV).

= = =

Jan, I’ve posted about this before in a number of other topics here. Think decision trees. I believe that both sitemaps and mindmaps potentially represent another kind of ontological tree that might be made available to AIML, for instance. Mindmapping is a hugely popular GUI for humans. There is a tremendous amount of “knowledge” currently “locked” in mindmaps, and unavailable to machines. Likewise sitemaps are hugely popular machine readable “trees” or outlines; but, their true value is currently unavailable to machines due to the “nesting” issue. (The ontological value is contained in the inaccessible nested *relations*.)

BTW, I always suspected that statistical AI techniques could be combined with pattern matching; so, your new tool sounds fabulous. I’ll have to give it a try.

= = =

> http://www.meta-guide.com/home/about/videography/best-gephi-videos

Gephi seems to be the preferred open source graph visualization option; however, it’s not yet clear to me the best way to import AIML. It seems that AIML would still need to be converted into CSV.

= = =

> http://www.meta-guide.com/home/about/videography/best-treemap-videos

I’ve also been looking at “treemapping”, and found this cool 2009 video on the work of Michael McGuffin, etc.

> http://www.youtube.com/watch?v=nvsIqYQ75yA

Elastic Hierarchies: Combining Treemaps and Node-Link Diagrams

= = =

Vince, sounds good!

> http://alicebot.wikidot.com/

The “Official Alicebot AIML Wiki” contains lots of AIML sets.

> http://code.google.com/p/aiml-en-us-foundation-alice/

See also the latest “Free A.L.I.C.E. AIML Set”.

= = =

Interaction Analysis of the ALICE Chatterbot: A Two-Study Investigation of Dialog and Domain Questioning (2010) http://w.icadl.org/intranet/papers/Schumaker_Interaction-ALICE_IEEE-SMCA_preprint.pdf

>> The Chat Engine is the core algorithmic component of the system and is comprised of two sub-entities; the Node Mapper and the Graph Master. When the system is initialized, the Node Mapper constructs a memory-resident directed graph of all the AIML patterns. Later, when a user poses a query to the system, the Graph Master will traverse the directed graph to best match the input. <<

= = =

> http://sourceforge.net/projects/program-n/files/

A working 2011 version of AIMLpad-1.54 seems to still be available from SourceForge, above.

> http://aiml.harrybailey.com/beta/

There is also Harry Bailey’s “AutoAiml 2.0 – free online Aiml Creator”, above.

= = =

http://alicebot.blogspot.com/2009/01/simple-aiml-editor.html

>>The SAE [Simple AIML Editor] is the latest development in the evolution of spreadsheet-style AIML editors like GaitoBotEditor and the Ai-Dealer AIML Spreadsheet editor.<<

= = =

> http://stackoverflow.com/questions/7530564/cannot-add-a-nested-relation-or-an-element-column-to-a-table-containing-a-simple

Cannot add a nested relation or an element column to a table containing a SimpleContent column

= = =

It seems that the “nested relations” represented in an AIML (XML) file cannot be converted directly into a spreadsheet.

This seems to be because the sub-elements of the various “trees” would have to have the same column name.

However, such “nested relations”, as represented in an AIML (XML) file, can apparently be represented in a relational database.

This would then require “XML to database mapping”, as well as “database to XML mapping”, bypassing the spreadsheet or CSV.

> http://www.altova.com/mapforce

Apparently, Altova MapForce is capable of this kind of “database mapping” to and from XML (AIML).

= = =

Can anyone check me on this, and confirm or deny all or part??

= = =

According to Richard Wallace:

>>Yes, that is exactly the problem. AIML is a special case of XML where the data is primarily row-oriented, spreadsheet style data. But one column, the template, contains hierarchical data. Most normal XML editors cannot be made aware of this hybrid structure.<<

= = =

> http://www.chatbots.org/ai_zone/viewthread/854/#12067

XPath seems to recognize the trees in an AIML file (see screenshot above link).

= = =

If each AIML template were auto-assigned a GUID, could the sub-elements of each template not be keyed to that GUID and uniquely auto-renamed, then be written to a conventional spreadsheet?

= = =

> http://www.chatbots.org/ai_zone/viewthread/854/#12174

I’ve just realized that what this is all about is the generation of machine written AIML.

Development › Platforms: Personality Forge API

http://www.facebook.com/pages/The-Personality-Forge/94470749322

= = =

http://www.personalityforge.com/chatbotapi.php

General › New here? And general stuff: JERVIS NEEDS HELP !!!

> http://twitter.com/mendicot/status/240816639900262400

Looking at @jervisproject .. The JERVIS Project http://jervis.net84.net .. (*not* “Project Jarvis” http://projectjarvis.com by @CBarraford) ..

= = =

> http://jervis.net84.net

Joseph, can you explain a little more about why and how Android apps need money to run? Why aren’t you charging money for Jervis? And, why isn’t Jervis on Google Play?

News & Events › In the news: A Working Theory of Love

> http://twitter.com/mendicot/status/252763649565921280

Reading @carolyn_cooke review of new chatbot novel by @smhutchi .. “A Working Theory of Love” http://goo.gl/9Y3pt ..

> http://twitter.com/mendicot/status/238008804208431104

Listening to @smhutchi talking about his forthcoming book, A Working Theory of Love http://goo.gl/AWLEs .. about fictional chatbot project

= = =

> http://twitter.com/HutchScott

Seems Scott Hutchins moved his Twitter account to @HutchScott ..

General › New here? And general stuff: HOw do I add a Chatbot?

> http://en.wikipedia.org/wiki/Scratch_(programming_language)

I’m guessing Neo’s chatbot is made in the Scratch programming language.

> http://www.meta-guide.com/home/about/videography/best-mit-scratch-videos

See my new Meta Guide webpage, “Best MIT Scratch Videos”.

> http://www.meta-guide.com/100-best-scratch-chatbots

And, “100 Best Scratch Chatbots”, above.

= = =

It seems these Scratch chatbots at MIT use a Flash interface, and might be possible to cut and past that Flash interface into other webpages, but could require some additional fiddling….

Development › Designing and coding: gesture tag for a chatbot with avatar

> http://en.wikipedia.org/wiki/Emotion_Markup_Language

Check out “Emotion Markup Language” (EML or EmotionML), above.

> http://en.wikipedia.org/wiki/RobotML

There is also the Robot Markup Language (RobotML), above.

> http://www.mindmakers.org/projects/BML

And, you might want to look at Behavior Markup Language (BML), above.

= = =

> http://www.daden.co.uk/wiki/pmwiki.php?n=AAML.AAML

The proprietary Daden “Avatar Action Markup Language” (AAML) was developed by David Burden for use in SecondLife.

> http://www.daden.co.uk/wiki/pmwiki.php?n=ASML.ASML

As was his “Avatar Sensory Markup Language” (ASML).

= = =

> http://elckerlyc.ewi.utwente.nl/

Elckerlyc is a BML (Behavior Markup Language) compliant behavior realizer for generating multimodal verbal and nonverbal behavior for Virtual Humans (VHs).

= = =

> http://www.meta-guide.com/home/bibliography/google-scholar/bml-behavior-markup-language-dialog-systems

I looked at “BML (Behavior Markup Language) & Dialog Systems”, above.

> http://www.meta-guide.com/home/bibliography/google-scholar/behavior-realizers

Apparently Elckerlyc is a “Behavior Realizer”, see above.

> http://smartbody.ict.usc.edu

In the world of BMLR (Behavior Markup Language Realizers), all roads seem to lead now to the University of Southern California Institute for Creative Technologies SmartBody project, above link.

> http://www.gestureml.org

FWIW, I also ran across the Gesture Markup Language (GestureML or GML), above link.

General › New here? And general stuff: Is it strange???

> en.wikipedia.org/wiki/David_Levy_(chess_player) [ http://goo.gl/7aI9K ]

Chess Master David Levy, and two time winner of the Loebner Prize (1997, 2009), authored a 2008 book, “Love and Sex with Robots: The Evolution of Human-Robot Relationships”.

> http://books.google.com/books?id=rM7WpdtOBVUC

In it, Levy examines how society’s ideas about what constitutes normal have changed, and will continue to change.

Development › Platforms: Skype versus Avatar platform

Fred, primo feedback, thanks!

By user friendly, I meant highest degree of customization for the lowest learning curve. I wasn’t considering computing overheads at all, which is why your experience is so valuable.

I’m definitely in the market for a SitePal alternative, not just a replacement, but something even better (and more affordable).

Supposedly the softcam (ManyCam) option would do away with the two computer solution.

Though single threading is another thing I hadn’t taken into consideration yet.

See my new Meta Guide webpages, “Best SecondLife Skype Videos” and “Best SecondLife Voice Videos” (below).

> http://www.meta-guide.com/home/about/videography/best-secondlife-skype-videos

> http://www.meta-guide.com/home/about/videography/best-secondlife-voice-videos

BTW, I did manage to visit Caesar Augustus in “Phaze Demesnes”.

= = =

Okay, so I made an initial test.

Of course, you need 2 wifi connected devices, and 2 Skype accounts.

ManyCam is a free download.

Open up the SecondLife viewer, set the ManyCam softcam to that piece of your desktop, then just set the Skype/Tools/Options/Video to “ManyCam Virtual Webcam”.

One thing I love about YouTube video tutorials is that you get 12 year olds teaching you how to do things you don’t have a clue about…. ;^)

> http://www.youtube.com/watch?v=HrZIU_L43Tw

I wasn’t really impressed by the audio quality coming out of SecondLife via ManyCam to the remote Skype.

And, not quite sure yet how to activate TTS & ASR for the NPC….

Development › My Chatbot Project: MS SQL Server based implementation of HAL or ALICE or MYBOT

> http://www.chatbots.org/expert/tom_joyce/612/

I believe 8man (above link) is a professional database programmer, and has experimented with as many natural language variants as anyone I know of.

I also believe Alicebot variant Program-O http://program-o.com is based on MySQL.

I’m intrigued about what it means to create a chatbot using only SQL.

I do know that some people in this forum prefer flatfiles over relational databases for the increased speed.

I got curious and did quick and dirty literature reviews on both “AIML & SQL” and “AIML & MySQL”, below.

> http://www.meta-guide.com/home/bibliography/google-scholar/aiml-sql

> http://www.meta-guide.com/home/bibliography/google-scholar/aiml-mysql

Development › Designing and coding: Tag a tweet

Jan, there has been a lot of work done already on Twitter sentiment analysis. There should be already tagged sets of tweets available. Most of the Twitter sentiment analysis I’ve seen works on simple positive, neutral, negative. More complex sentiment analysis would be nice. Robert Medeksza has done a lot of work with Twitter for his Ultra Hal, though don’t know about with sentiment analysis per se.

> http://www.meta-guide.com/chatbots-sentiment-analysis

I’ve used Twitter sentiment analysis to look at the relative popularity of SimSimi vs. Cleverbot.

> http://www.meta-guide.com/home/bibliography/google-scholar/open-source-sentiment-analysis-tools

And, I’ve looked at open source sentiment analysis tools in the context of dialog systems.

= = =

> http://www.mturk.com

Jan, I seem to recall that a lot of people use the Amazon Mechanical Turk (above link) for those type of human training tasks.

Development › Designing and coding: Simple Knowledge Base Interface

> http://wiki.dbpedia.org/lookup/

I just set up the DBpedia API (above link) in Yahoo! Pipes, which seems to work fine to lookup “Wikipedia” data, such as it is.

General › AI thoughts: If you could add anything to siri

– API / SDK (customizable backend)

– Avatar (customizable frontend)

= = =

No logo, no text input, just a talking head, any talking head, like my own for instance, or even a kangaroo…. ;^)

=> http://www.youtube.com/watch?v=keCG57A7b1w

Development › RiveScript: RiveScript Bot Hosting BETA

WAAAY COOOL… THANK YOU, THANK YOU, THANK YOU… NOAH !!

I made a bot and got the API working in Yahoo! Pipes. Will try downloading and uploading KB next.

Something funky was happening with uploading of profile pic…. There seems to be too much mess in the profile; I’d prefer to have all the options optional….

= = =

“Download your bot’s brain” doesn’t seem to include “Base brain” (for instance, Alice). I’d like to be able to see the “Base brain” too in order to compare side by side with AIML; because, I need to use offline power tools to bulk convert my AIML into RiveScript. Unless you have a AIML-to-RiveScript converter already? In fact would be a cool feature to be able to upload AIML and have it auto-convert into RiveScript…. ;^)

= = =

> http://apiary.io/

I’ve recently found an “API documentation generator” (@apiaryio), which might help document the API.

> http://www.mashape.com/

It might be worth looking into offering the RiveScript API on @mashape (Cloud API Hub); for example, @pannous offers their “virtual assistant” API on Mashape (below).

> http://www.mashape.com/pannous

Development › Designing and coding: Some issues

> http://www.meta-guide.com/home/bibliography/google-scholar/construction-grammar-dialog-systems

It seems to me that “grammar parsing” is involved with the *de-construction* of natural language; so, how is natural language *re-constructed* or “generated” from parsed grammar ?!? And, what are examples of a tools or systems that do this ?!?

= = =

I’m just finding it hard to believe that all “grammar parsing” dialog systems (grammar agents) depend on machine learning to generate natural language responses….

> http://www.meta-guide.com/home/bibliography/google-scholar/rule-learning-dialog-systems

Is it correct that “decision trees” are generated by “rule learning systems”?

> http://www.meta-guide.com/home/bibliography/google-scholar/learning-classifier-dialog-systems

And, are “rule learning systems” not otherwise known as “learning classifier systems”?

= = =

> http://books.google.com/books?id=r3OTcQo3C7QC

Reinforcement Learning for Adaptive Dialogue Systems: A Data-driven Methodology for Dialogue Management and Natural Language Generation (2011)

= = =

> http://www.meta-guide.com/home/bibliography/google-scholar/classifier-dialog-systems-2011

I looked at 365x academic papers from 2011 about dialog systems mentioning “classifier” (above).

> http://www.meta-guide.com/home/machine-learning/classifiers-in-dialog-systems

From those 2011 papers, I manually extracted some 122x classifier terms, or “types” of classifier (above). I then scored those classifier types for “popularity” against the past 10 years of papers in Google Scholar (above).

> http://www.meta-guide.com/home/machine-learning/classification-algorithms-in-dialog-systems

Then I took the whole “Category:Classification_algorithms” from Wikipedia (circa 125x) and scored those for popularity against the past 10 years of papers in Google Scholar (above).

> http://www.meta-guide.com/home/machine-learning/best-dialog-system-classifiers

Looking at the top dozen from both lists, I created a new Meta Guide webpage, “Best Dialog System Classifiers” (above).

= = =

It is still not clear to me whether or not all or most grammar based (grammar parsing) dialog systems (grammar agents) necessarily require machine learning and/or classifiers in order to generate natural language responses ?!?

What is more clear to me is that I now suspect that the “learning classifiers” create the so-called “language model” that the dialog system uses to “map” replies….

For instance, three forms of feature may be incorporated into the classifier: part-of-speech (POS) tags, lexical features, and syntactic properties.

The classification function can be defined in several ways: a multi-nomial naive Bayes classifier, a n-gram based classifier, a classifier based on grammatical inference techniques, or a classifier based on neural networks.

Basically, classifiers may be statistical or rule-based.

Development › Platforms: Beyond Virtual Avatars

It seems there has been a good bit of debate on the conspicuous absence of *convenient* avatar solutions. I haven’t really seen a consumer product better than the $40 a month SitePal for the web. There is now @Sparking2gether FIONA; but, I haven’t actually seen any deployed solutions yet. For the desktop, there is Guile3D Denise. But, I’ve not seen any *generic* consumer oriented avatar solution for mobile yet, much less multi-platform.

Another thing that I’ve noticed is that no one seems to be making affordable plug and play talking heads. What I’m thinking of here is (cheap) life-size animatronic talking head with plug and play USB or wifi. Of course, there is Hanson Robotics at the custom high-end, but not much in the mid-market or low-end.

> http://www.meta-guide.com/home/about/videography/100-best-hanson-robotics-videos

> http://www.meta-guide.com/home/talking-head/100-best-animatronic-head-videos

> http://www.meta-guide.com/home/talking-head/100-best-robot-head-videos

See my recent Quora answer to: “I’d like to build a talking animatronic Beethoven bust for my music room, and don’t even know where to begin, how to get started?”

> http://www.quora.com/Robots/Id-like-to-build-a-talking-animatronic-Beethoven-bust-for-my-music-room-and-dont-even-know-where-to-begin-how-to-get-started

= = =

> http://www.meta-guide.com/home/about/videography/best-haptek-videos

At this point in time, I consider Haptek to be outdated technology; although, it was certainly an extremely user-friendly, generic avatar system. I’m in touch with Chris Shaw (http://chrisshorts.com/) about his new project, Xprevo (http://xprevo.com/); and as far as I can tell, Xprevo will be nothing like Haptek.

> http://www.meta-guide.com/home/about/videography/best-wowwee-elvis-videos

I didn’t know about the WowWee Chimp, but did find a few more videos.

> http://www.meta-guide.com/home/about/videography/100-best-nabaztag-videos

In terms “toy” talking “heads”, it might also be worth taking a look at Nabaztag (aka “Karotz”).

Development › ChatScript: What basic tutorials and manuals exist for chatscript for an absolute beginner?

> http://www.meta-guide.com/chatscript

I’ve started a Meta Guide webpage on “ChatScript” (above link), where I’m trying to centralize resources to better understand it myself.

What I would really like to see are more VIDEOS; simple narrated screencasts are fine. What I’m particularly interested in seeing are installation procedures, especially mounting on remote servers (something like Heroku or AppEngine for instance). Also, anything about an API, for instance setting up a web API for ChatScript.

= = =

> http://sourceforge.net/projects/bot-framework/

Any idea who the “crazy_chris” is behind “Advanced Bot Framework” (Last Update: 2009) ??

Development › Platforms: Internet Relay Chat Bots

>> @erwinvanlun .. FYI, just noticed @chatbots seems to have no Directory listing for Platforms => IRC .. Sat Jun 11 17:19:36 +0000 2011 <<

= = =

> http://www.meta-guide.com/irc-chatbots

I’ve been researching IRC bots lately, above link. I have noticed that very often IRC “do-engines” are erroneously referred to as “chat bots”. This has lead me to postulate a new theory for the origin of the term “chat bot”. I believe that “chat bot” may have come about in reference to “Internet Relay Chat” shortened to just “Chat”; therefore any IRC bots may have been referred to as “Chat bots”. I found it peculiar that so many “do-engines” were apparently erroneously being referred to as “conversational agents”; natural language commands to not a “chatbot” make….

What do you think about this? Can you confirm or deny my supposition?

See also “N-gram Timeline”:

> http://www.meta-guide.com/ngram-timeline

Development › Designing and coding: Some issues

> http://www.meta-guide.com/home/bibliography/google-scholar/stanford-nlp-dialog-systems

> http://www.meta-guide.com/home/bibliography/google-scholar/nltk-dialog-systems

CR, what I am not clear about is the interpreter for a parsed grammar…. There is a HUGE body of work on grammar parsing, but I’m having trouble finding anything on natural language interpreters for parsed grammars. Basically, what the heck do you do with a grammar once it’s parsed? I mean, how do you get from parsed grammar to natural language interpretation and interactive chatbot? Where are the tools for doing this? I’ve never seen a tool where you can just upload a parsed grammar and talk to it….

= = =

> http://www.meta-guide.com/home/about/videography/best-natural-language-parsing-videos

I recently put together a Meta Guide webpage on “Best Natural Language Parsing Videos”, with links to other pages on various kinds of parsers.

> http://www.meta-guide.com/home/about/videography/100-best-decision-tree-videos

I’ve also put together a webpage on “100 Best Decision Tree Videos”, with links to pages on other kinds of “trees”.

= = =

I like Robert’s term “grammar agents” to describe these kinds of conversational agents; but, there is almost nothing in the academic literature referring directly to “grammar agents” as such.

Jan, can you briefly describe in general terms (or post a link) how your “decision trees” work with your “neural network” to generate a natural language response?

And, what is the relation of trees to graphs, if any?

= = =

> http://www.meta-guide.com/home/bibliography/google-scholar/decision-tree-dialog-systems-2011

Okay, I made a new Meta Guide webpage for “Decision Tree & Dialog Systems 2011”.

> http://www.meta-guide.com/home/bibliography/google-scholar/random-forest-dialog-systems

And, I also made one for “Random Forest & Dialog Systems”.

= = =

Basically, these pages represent a quick and dirty recent literature review. It was interesting for me that just in 2011 there were over 200 papers mentioning decision trees and dialog systems, which is a large number; to me, this means that this technique is much more popular than I had realized.

Perhaps logically enough, a random forest can be defined as many decision trees. There were not that many papers from the past ten years mentioning random forests and dialog systems; however, as usual I ran a word cloud on my results, and fascinatingly EMOTION popped out on top. I interpret this to mean that random forests are most often used in dialog systems for the purpose of computing affect.

= = =

So then, can it be said that there are three main kinds of dialog systems?

1) Pattern matching

2) Probabilistic

3) Grammar agents

I’m still not clear about what the major examples of “grammar agents” are. For instance, are there examples of open source dialog systems based on “grammar parsing”, or implemented “grammar parsing” dialog systems presented online in an interactive format??

Development › Designing and coding: Simple Knowledge Base Interface

> http://www.meta-guide.com/home/application-programming-interfaces

Web APIs, I love web APIs. I use Yahoo! Pipes for all web APIs. When I have a decent dialog system web API available, I don’t have any trouble integrating it with Pipes. Your most basic knowledgebase format is a text file, which can be saved as CSV. Your next most basic format is any spreadsheet. Pipes is great because it has a CSV module to integrate virtually any spreadsheet, hosted on Google Drive for instance. Unfortunately, Yahoo! Pipes chokes on large and complex integrations; so, lately I’ve been looking into iPaaS (integration Platform as a Service), though have yet to find just what I’m looking for….

> http://www.meta-guide.com/home/ipaas-integration-paas

See also AI Middleware:

> http://www.meta-guide.com/home/artificial-intelligence-middleware

Development › New to Chatbot programming: Need help with voice recognition

> http://www.quora.com/Speech-to-Text/What-open-sourced-and-accurate-speech-to-text-engines-and-APIs-currently-exist

See my recent Quora answer to: “What open-sourced and accurate speech-to-text engines and APIs currently exist?”

> http://www.sitepal.com/packages/

SitePal offers a Pandorabots-compatible TTS avatar for “Artificial Intelligence” at $40 per month.

You can get STT (ASR) using the Google (Chrome) Speechrecognition API, see attached screenshot.

= = =

> http://chrome.google.com/webstore/detail/voice-in/gjkogfbjkfchelfjonefnnenhfgglpnn

Try installing this Chrome plugin “Voice In”.

Development › AIML & other standards: PyALICE Story

> http://www.ohloh.net/p/pyalice

What ever happened with PyALICE? It seems to have disappeared from both Google Code and Google Groups….

Development › My Chatbot Project: Type III

Vincent, do you have a YouTube channel? Some people prefer screencast videos of someone in the know putting chatbots through their paces, showing what they are capable of, like demo videos. Narrated screencasts are not too hard to make. In fact, there are lots of videos on YouTube of young people railing at text based chatbots with hilarious adlibs. BTW, I’ve been using semi-automated tools to build up my “Meta Guide Videography (Best of the Best Videos)”, below.

> http://www.meta-guide.com/home/about/best-of-the-best-videos

General › New here? And general stuff: Start?

> http://www.chatbots.org/se

Amanda, if you want to find Swedish chatbots to chat with, just check the above link.

If you want to make your own chatbot, check the “Build your own” links from the Chatbots homepage (attached).

= = =

Where is the URL indeed! This a something I have also struggled with. A chatbot may live on your desktop or live on a network server. The tricky part is that your desktop may also be used as network server. If the chatbot lives on a remote server, then we can say it lives in the cloud. There are many web services where you can make chatbots that live remotely in the cloud; however, very often you may have to download the chatbot knowledge to work on it on your desktop. Another tricky part is that most command-line chatbot programming has to be first built on your own desktop machine before it can be pushed or “published” to a remote server. If the chatbot is on your own desktop, you may access it through your browser – even if offline, or there may be another interface, text or graphic, that is not dependent on the browser. Honestly, I have found no perfect way to make a chatbot yet, though probably Pandorabots comes the closest. This is one reason I’ve come to prefer web APIs, because at least you know where the darn URL endpoint is…. ;^)

News & Events › New chatbots: Harumi

Jean-François, can you confirm that Harumi is only available for the desktop via download? I really hate putting software on my machine, especially non-Windows programs. If Harumi is available on the Web or via mobile app, I can probably find some testers for you. Do you have any plans for a mobile voice app?

General › New here? And general stuff: Introduction

> http://twitter.com/mendicot/status/253899797646438400

Checking out new AI .. RICH (Realm of Illusions Cybernetic Human) http://ai.r-i-software.com .. Vincent GIlbert @risoftdev creating cyberself ..

= = =

Hi Vincent, I’m a big fan of connecting dialog systems with social media, for Social CRM. If you’ve got an API for RICH and are interested in hooking it up with Twitter, just let me know and I can suggest a number of ways to do it.

Development › New to Chatbot programming: Program O and Wikipedia

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

James, you might want to look at University of Waikato WikipediaMiner. (Note, Waikato also does the popular Java machine learning package “WEKA”.) I know that there are many sub-sets and corpora of Wikipedia available in a variety of formats. I believe Paul Allen’s “Digital Aristotle” Projecthalo.com has even based their knowledgebase on the humanly editable “wiki” format.

= = =

Karsten, do you offer customizable versions of your API? I mean the base API plus additional custom knowledge?

> http://guile3d.com/en/forum/wish-list-features/higher-education-learning-management-systems-lms-and-artificial-intelligence/#p6236

I recently sent the same question to Existor (above), but have gotten no response from them….

News & Events › New chatbots: The 2012 Debates – Romney Bot vs Obama Bot

> http://twitter.com/mendicot/status/243694987114586113

Political chatbots: @SoapBoxingGame by @Cepstral_LLC .. Nutbots http://nutbot.net by @CereProc .. http://askthecandidates2012.com by @Medeksza ..

> http://twitter.com/mendicot/status/253488202982227968

New political chatbots .. Romney vs Obama Debate Bots http://goo.gl/2A4IW .. includes ChatScript, AIML & Wolfram_Alpha .. by @Ferd_Frederix

News & Events › New chatbots: Neat chatbot at United.com

> http://twitter.com/airlinesagent

“Next IT conversational virtual agents for airlines deliver perfect web customer service, offering a direct connection to the information your customers need.”

> http://twitter.com/mendicot/status/252770686404268032

Watching videos .. @Next_IT Human Emulation Technology (1of2) http://youtu.be/Qd1C50XfxyQ .. (2of2) http://youtu.be/kk2rWIxegME .. by @chuckw

Development › ChatScript: Introduction

> http://twitter.com/mendicot/status/252764377382539264

Added new semi-automated Meta Guide webpage, Best Virtual Patient Videos http://goo.gl/lCCJT .. all about virtual patients & virtual nurses

Development › My Chatbot Project: Is it possible to make chatbot in 7 months

Making a chatbot and making a chatbot engine are two different things. There are a number of good chatbot engines already available, such as Program O, ChatScript, and RiveScript. I honestly do not see the point for you to create another chatbot engine from scratch. AIML is a chatbot language, for instance various chatbot engines use the AIML language, such as Program O. Creating a chatbot, or virtual personality, on a chatbot engine is a whole nother can of beans. One does not enter a chatbot engine per se into the Loebner Prize; one enters a chatbot, or virtual personality built upon a chatbot engine, using a chatbot language. And, it could easily take 7 months just to create a virtual personality, which might be barely competitive in the Loebner Prize.

A grammar parser is neither a chatbot engine nor a chatbot language. In fact, I wish someone would provide an example of a natural language interpreter for a grammar parser. My understanding of a grammar parser is that one would more likely convert a parsed grammar into a chatbot language for use in a chatbot engine, or chatbot language interpreter.

IMHO, what would be more productive would be to use your enthusiasm and programming skills to create a cloud-based commercial web service, dialog system API, with Program O, ChatScript, or RiveScript. Of the existing cloud-based consumer dialog systems, including @bot_aco, @chatbot4u, @mycybertwin, and @pandorabots… Pandorabots is the only one that offers a fully customizable knowledgebase, downloadable and uploadable, as well as an API http://bit.ly/Ihg9eH . What it does not offer is a backend API for modifying the knowledgebase automatically, without downloading and uploading for offline modification. It also does not offer turnkey bindings to popular social networks, for the purpose of Social CRM.

Development › My Chatbot Project: Kill Me Now!

> http://acobot.com/

Lawrence, what you need is an automated Acobot popup “chatbox”, the quickest and easiest solution for you. FYI, you ought to downgrade the vanity pic of yourself to an “About” page, and consider just a headshot, though it certainly gives the immediate impression of “hair-raising dates”. ;^)

= = =

> http://wordpress.org/extend/plugins/acobot/

Well, you’re in luck; Acobot offers a dedicated WordPress plugin.

News & Events › New chatbots: Natebot

> http://twitter.com/mendicot/status/246221907836403713

Erwin, I think you’re being a little hard on him. It’s actually very original. I love seeing non-standard interfaces. And, I think it’s supposed to sound like a “robot”. Also, sourcing answers from chacha.com is unique; I don’t know of any other chatbots that get their answers from chacha. Thanks for the pointer though!

Development › My Chatbot Project: Rating a blob of text

> http://www.quora.com/Text-Analytics/Are-there-any-online-Bayesian-SaaS-text-classifiers-apart-from-uClassify-com

I have found that the deeper you go into *meaning* (the meaning of meaning) the murkier it gets. Semantics, that’s really the $64,000 Question, isn’t it? My understanding of neural networks is that it’s not very well understood. Learning, the extent of my foray into machine learning for chatbots has been classifier APIs; see my Quora answer to: “Are there any online Bayesian SaaS text classifiers apart from uClassify.com?” (above link).

Triples have been a recent revelation for me, so simple yet so obscure. Triples are basically simple sentences, with subject, predicate and object. Triples represent relations, meanings beyond the words. Thus, if your text is annotated with semantic metadata, you should be able to apply a semantic reasoner, or OWL reasoner. I don’t know of any available dialog system that is build primarily upon semantic metadata, or semantic reasoner.

Then there is the statistical approach. I’m not convinced that n-grams are adequate. For myself, I prefer skip-grams (s-grams), or “gappy” n-grams. However, in the end, what even qualifies as hit or miss in terms of answers? I’m not a fan of the Turing test anyway, and believe it to be a red-herring. Who needs machines that can fool people anyway? I want to skip forward directly to machines that are way better than people, at certain things, and therefore be used as better tools….

Development › My Chatbot Project: Chatbot API

As far as I know, there is no web-based (cloud) dialog system API (web service) with both frontend and backend (incoming and outgoing) APIs. At this point, everything close is highly customized, hand-cobbled and brittle, not to mention otherwise exorbitantly expensive. You might like to check out my recent videos on “Open Chatbot Standards for a Modular Chatbot Framework” http://bit.ly/r7fj8D , and may also wish to take a look at my Meta Guide webpage all about “Jabber, XMPP & Chatbots” http://bit.ly/K9jw1Z (AIM, gtalk, etc).

News & Events › New chatbots: testing the self-awareness of our bot – digital radio interview

> http://twitter.com/mendicot/status/243450437292941312

Listening to @PeitzkerTania .. talking about her new AI @myownreporter http://goo.gl/37jGU .. powered by #velmai .. (via @coastfmcairns)

> http://twitter.com/myownreporter

Tania, you ought to add a pic and link to your @myownreporter Twitter profile (under Settings). If you really want to get some attention, you should hook your AI up to that Twitter account – so punters can interact with it themselves.

General › New here? And general stuff: Hello from Will Dockery

Hi Will, I would be interested in hearing more about what you like most, and what you like least about MyCyberTwin ..

BTW, you’re in Georgia? There’s a well known musical chatboticist in Georgia, Robby Garner; check out his chatbot stuff at http://www.robitron.com .. and his musical stuff at http://www.fluxoersted.com ..

= = =

Will, you make some interesting points.

A user community is a basic self-service support system for any startup.

I haven’t found the folks who run MyCyberTwin to be particularly accessible themselves.

MyCyberTwin does have an API, but it’s only available to enterprise clients, hence exorbitantly expensive.

MyCyberTwin does have a way for your CyberTwin to square off with other MyCyberTwins => http://mycybertwin.com/ui/aivsai.jsp

A web feed of conversations is a wonderful feature; the only one I’ve noticed being promoted as such was ShakespeareBot by Program-O creator http://Elizaibeth.com , but which seems to be offline now.

Let me know anything else that might pop up on your wish list!

Development › AIML & other standards: is it possible?

> http://www.pandorabots.com/botmaster/en/faq#h2

Pandorabots has an API.

> http://www.geekcavecreations.com/v2/gui/

Apparently, the new version of Program O has an API.

The problem is that the backend of Pandorabots does not have an API for dynamically modifying the knowledgebase. It’s complicated, apparently there’s a premium version of Pandorabots for professionals, and a hack using the <learnf> tag to kinda, sorta automate modifications, which is not available on the free version.

I’m presently looking into iPaaS (integration PaaS) in order to more actively integrate APIs at all levels.

> http://www.meta-guide.com/home/ipaas-integration-paas

= = =

> http://www.quora.com/Natural-Language-Processing/Which-topics-on-Quora-are-related-to-the-technology-behind-Apple-Siri

For something about the tools (CALO/SPARK) originally used to integrate Apple Siri’s more than 35 APIs, see my recent Quora answer to: “Which topics on Quora are related to the technology behind Apple Siri?” (above link).

News & Events › New chatbots: First Program-O Twitter Bot

> http://twitter.com/mendicot/status/234734678693777409

New Twitter chatbot .. @grassbrig made in Oregon by @rebelwords .. now engaging other Twitter chatbots http://goo.gl/4GAuU .. #rebelAI

> http://twitter.com/mendicot/status/235039839899230208

RT @rebelwords: Thanks for allowing me to test @grassbrig (php/oauth/#programo). I’ll blog it once I clean it up.

General › New here? And general stuff: Chatbot.com Still For Sale, 10+ Years Later

> http://www.sedo.com/search/details.php4?domain=chatbot.com

Not only is Chatbot.com still for sale, according to the Internet Archive Wayback Machine seems to have been for sale for more than 10 years….

> http://wayback.archive.org/web/*/http://www.chatbot.com/

= = =

> http://en.wikipedia.org/wiki/Cybersquatting

Steve, Fabulous.com is probably either a domain speculator or their representative; just look at their server names, “buy” and “sell”.

Development › New to Chatbot programming: Where to begin? -Huge goals-

> http://www.meta-guide.com/vehicle-telematics

I’ve got a Meta Guide webpage full of resources on “Dialog Systems in Vehicle Telematics” (above), which may help; let me know if I should add anything!

Development › RiveScript: RiveScript? In my web browser? Introducing RiveScript.js!

> http://www.rivescript.com/demo/rivescript-js/

Noah, it looks beautiful!

General › New here? And general stuff: Get Well Soon Dave

Well, on the bright side, what a fortuitous opportunity to put some of this assistive technology to the test!

= = =

Dave, that could be a significant finding right there! Obviously, this stuff is not yet easy enough for real people to use (as opposed to geeks). In fact I’ve maintained that all along. Just take Program-O for instance or even Chatscript, they are just not up to the job for real people, in real life.

When people talk about AGI (artificial general intelligence), they often mention self-programming machines; well, what about self installing/configuring chatbots in the form of assistive agents? Take something like Guile3d Denise for instance; in your situation, you should be able to just flip the switch, and get her to do things for you (like type, etc)….

Development › Designing and coding: Natural language decomposition

> http://en.wikipedia.org/wiki/Decomposition_(computer_science)

“a complex problem or system is broken down into parts that are easier”

In the “other strategies” category, I’ve been experimenting with a system that dispenses with both “database” and “interpreter” altogether. There are now many web APIs that can do named-entity recognition (NER), some better and some worse.

I’ve got a working prototype that extracts questions directly from the Twitter API, extracts named-entities, and then searches the Twitter API for likely candidate replies. The replies appear to come from a “virtual agent”, however are linked back to the original tweet, in effect connecting the “questioner” with the “answerer”.

This technique is vaguely reminiscent of Omegle or the infamous AIM bot, TheGreatHatsby, as well as the so-called Fish Bots, that pair up users in various ways.

> http://en.wikipedia.org/wiki/Omegle

> http://web.archive.org/web/20081220145156/http://en.wikipedia.org/wiki/TheGreatHatsby

Development › Platforms: Conversive Verbots Online Closing Down

Verbots Online Service Discontinued effective August 31 http://www.verbots.com/forums/viewtopic.php?t=3636

Verbots Online closing down at the end of August http://www.verbots.com/forums/viewtopic.php?t=3637

= = =

> http://twitter.com/mendicot/status/245479984272134144

As of yesterday, the cloud hosted http://VerbotsOnline.com ceased operation; however, their desktop version lives on at http://Verbots.com 🙁

> http://twitter.com/mendicot/status/245481032273506304

You can read more about the history, ups and downs, of Verbots (Verbal Robots) on their new “Official Verbots Blog” http://verbots.blogspot.com ..

> http://twitter.com/mendicot/status/245483094625366016

Reading Wikipedia .. Verbot (Verbal-Robot) http://goo.gl/YOxVl .. originally developed by @TeamToad & @thenar ..

> http://twitter.com/mendicot/status/245483747733041152

Watching video .. “TEDxMunich – Peter Plantec” http://youtu.be/7BR5r2TL1uM .. @thenar on Verbots, Virtual Personalities & Virtual Humans ..

> http://twitter.com/mendicot/status/245484459116359680

In honor of Conversive VerbotsOnline going out of business .. I’ve added a new Meta Guide webpage “Best Verbots Videos” http://bit.ly/T3e8UB

> http://twitter.com/mendicot/status/245485914623725568

Conspicuously absent from Twitter, Verbots parent company Conversive, Inc http://conversive.com can be found on LinkedIn http://goo.gl/k2D10

> http://twitter.com/mendicot/status/245487086201864192

Alternatives to Conversive VerbotsOnline include .. @bot_aco .. @chatbot4u .. @mycybertwin .. @pandorabots ..

= = =

> http://twitter.com/mendicot/status/254637894289993728

Matt Palmerlee @mpalmerlee is looking for help to open source a simple text only version of VerbotsOnline via github http://goo.gl/JzxkJ ..

News & Events › Events: SAVE DAVE

Yo Dave, don’t you have a chatbot that you can just talk at and get it to do things for you, like type?? I just got CallMom on my new Nexus 7 tablet, and the ASR is pretty darn good!

General › New here? And general stuff: Looking for a starting point

Starting pint accepted via http://tweet-a-beer.com to http://twitter.com/mendicot

General › AI thoughts: Standards organization?

> http://www.meta-guide.com/home/open-chatbot-standards

Don’t miss my recent videos on “Open Chatbot Standards for a Modular Chatbot Framework”.

> http://en.wikipedia.org/wiki/Open_Mashup_Alliance

More recently I’ve come across the Open Mashup Alliance, “a non-profit consortium that promotes the adoption of mashup solutions in the enterprise”.

Development › Designing and coding: Sending Alert messages using chatbot in app engine

> http://www.meta-guide.com/jabber-xmpp-chatbots

Jabber, XMPP & Chatbots

XMPP is generally used for instant messaging, and App Engine is compatible with XMPP. If you are using Gmail for instant messaging, then I believe you would need an email address list. Chatbots per se are notorious for being reactive, and not proactive. Chatbots are good for answering questions, but usually not for initiating conversations. In general proactive “chatbot” systems fall under the rubric of “spambots”….

Development › ChatScript: Starting with AI

> http://www.youtube.com/user/aimlinstructor/videos?sort=dd&query=aiml&view=0&page=2

See the earlier videos under aimlinstructor at YouTube, above link.

> http://www.pandorabots.com

Start with Pandorabots.com. Once you get comfortable with AIML, then you can go on to PHP Program-O using MySQL.

> http://blog.program-o.com

= = =

A dialog system is most basically a kind of search engine, with text in and text out.

You send text in over an API or GUI, a kind of search is performed, and you get text out.

So, you might think of a dialog system as your own mini search engine.

In making the database, or what we call a knowledgebase, you get to choose which replies would be best.

The interpreter then traverses knowledge trees until arriving at the given answer.

Text in, text out .. you write the database .. and the interpreter searches out your response.

= = =

I don’t actually use Program O, mainly because it’s just too onerous for me to deal with. You may have to wait until Dave recovers from his accident sufficiently. I think in this case more screencast videos are needed; as far as I know, there are no good how-to videos available for working with Program O. I especially appreciate quickstart videos.

General › New here? And general stuff: Chatbot Orgs getting slower and slower

> http://cloud.google.com/compute

I did bring this issue to Erwin’s attention not long ago. Chatbots.org is one of the slowest sites that I frequent. I *imagine* it sitting on a machine in someone’s home somewhere. It should probably migrate to the cloud, like AWS or perhaps the new Google Compute Engine, above link. It is showing a decent valuation on WideStat, below….

> http://widestat.com/chatbots.org

>> Chatbots.org Estimated Value $17978.40 USD

Development › Platforms: Use of Botplatform

> http://www.meta-guide.com/jabber-xmpp-chatbots

Jabber, XMPP & Chatbots

> http://www.meta-guide.com/best-xmpp-videos

Best XMPP Videos

> http://twitter.com/BotPlatform

BotPlatform hasn’t posted to their Twitter account since August 2010….

> http://botplatform.googlecode.com

You can also find BotPlatform on Google Code; I wonder if BotPlatform might not be a substitute for IMified.com?

> http://www.twitonmsn.com

It seems that BotPlatform powers TwitOnMSN.com, which means that one might be able to use it to connect Pandorabots for instance to Twitter….

= = =

http://en.wikipedia.org/wiki/Microsoft_Lync

>>Microsoft Lync and Microsoft Lync for Mac are enterprise software; unlike Windows Live Messenger, they have a different feature set that is targeted toward corporate environments.<<

http://en.wikipedia.org/wiki/Unified_communications

>>Unified communications (UC) is the integration of real-time communication services such as instant messaging (chat), presence information, telephony (including IP telephony), video conferencing, data sharing (including web connected electronic whiteboards aka IWB’s or Interactive White Boards), call control and speech recognition with non-real-time communication services such as unified messaging (integrated voicemail, e-mail, SMS and fax).<<

= = =

>>Watching video .. “How to use WorkerBee Chat Bot” http://youtu.be/-ORHU0iTPUI .. IM monster bot by @ToplisterCash .. ?#therealTopVader?<<

Harshit, interesting choices. Just yesterday I happened across this “Worker Bee” monster IM bot, above, supposedly free. More related to Lync, I’ve seen a lot of “chatbots” for the Campfire software, a web-based, business-oriented online chat service by @37signals. Be aware, very often when people talk about “chatbots” for IRC, IM or chatrooms, they are not necessarily referring to natural language dialog systems, but rather to various kinds of control and utility programs.

Development › Designing and coding: Natural Language Generation

> http://www.meta-guide.com/nlg-natural-language-generation

Merlin, you can see my Meta Guide webpage on NLG, above; note links to related Meta Guide pages at bottom.

> http://www.quora.com/Natural-Language-Generation

There is also a link to the NLG topic on Quora; note the relation to the current practice of “autoblogging”, which in turn is related to the new Weavrs.com “infomorphs”, see link below.

> http://en.wikipedia.org/wiki/Infomorph

I would say the most common implementation of “NLG” is probably the plethora of Markovian scramblers.

= = =

> http://betabeat.com/2012/07/mark-v-shaney-horse-ebooks-markov-chain-twitter-07022012/

Here’s a more recent post about Mark V Shaney, above link.

> http://www.meta-guide.com/100-best-autoblogging-videos

100 Best Autoblogging Videos

> http://www.meta-guide.com/best-wordpress-autoblog-videos

Best WordPress Autoblog Videos

> http://www.meta-guide.com/best-wordpress-tweetoldpost-videos

Best WordPress Tweet Old Post Videos

> http://www.quora.com/Autoblog

Most autoblogging is happening in the WordPress world .. and @Weavrs are apparently based on “heavily mutated” WordPress, called UberStream ..

= = =

Why are pirate technologies like “autoblogging” interesting, and how do they relate to natural language generation?? Autoblogging is closely related to the “robojournalism” of companies such as Narrative Science (@narrativesci) and Automated Insights (@AInsights), mentioned in Merlin’s NPR link above, that are generating prose out of raw data. So what is the difference between blackhat autoblogging and whitehat robojournalism? I suggest that the difference is basically Markovian, related to the level of gibberish and its relevancy.

Questions and answers, QA systems, go two ways. How do you generate blogs automatically, and how do you generate news articles automatically?? Just look at the converse, how we generate answers from questions “asked” of blogs and news…. Not only can we generate answers to questions by “searching” online; but, we should also be able to do the reverse with similar technology, construct textual material, such as blog or news, via dialoguing simply by framing the questions right…. ;^)

= = =

Let’s get unstuck from the Turing test model for a moment, and look at the mirror image of this story…. Of course we create bots to mimic people. But what if we created a bot to write essays for us, simply based on our oral outline? So instead of getting the bot to summarize the web for us, the bot would expound textually on our oral summary…. I think my point is that if we can can use the web to generate human-like responses, in other words answers, why can’t we do it the other way round and just use our human responsiveness to generate web-like results? This would be like a Turing test based on human products, for instance essays, created from dialog, rather than based on the dialog itself….

General › New here? And general stuff: rep.licants.org

> http://topsy.com/rep.licants.org

I’m not convinced that rep.licants.org is better than weavrs. Weavrs seems a bit more production ready.

At the above Topsy link, you can see what everyone has said about rep.licants.org on Twitter.

You can see also both:

> http://topsy.com/www.weavrs.com

> http://topsy.com/weavrs.com

The 2010 video below is the best one I’ve found about Weavrs.

> http://www.youtube.com/watch?v=Dq9BRAaYyIg

= = =

http://prosthetics.weavrs.com/2011/asking/

>>Their chat abilities are based upon the ALICE chat system developed by Dr Wallace. The ALICE system adds a conversational, natural language interface to the narrative filtering processes that Weavrs perform.<<

General › New here? And general stuff: Introduction

> http://twitter.com/mendicot/status/199813134825955328

Artificial intelligence will make “Republicans” obsolete; because, the only way forward in a labor force dominated by robots is socialism ..

= = =

> http://www.meta-guide.com/home/twitterbots/weavrs

Hi Abel, you should check out the whole @Weavrs trip (see above link); they are “socialbots” being referred to as “infomorphs”….

> http://en.wikipedia.org/wiki/Infomorph

Development › AIML & other standards: Realtime AIML

I’ve gotten to the point where I can supply an XML feed of dynamic AIML. But, what to do with it?

Is there any cloud based platform with an API able to receive and store such dynamic AIML, and with an interpreter API that could access it in near realtime??

If nothing like this exists as a service, what are the alternatives? What would a theoretical configuration look like?

= = =

Basically, I’m now able to convert web feeds into AIML with semantic APIs. My questions are now, how to “store” this dynamic AIML in such a way that it’s available to an interpreter API with the least amount of latency, as well as how to accomplish this with the least hardware and programming overhead?? The idea is to create “ephemeral” AIML for realtime programmatic interpretation.

Development › AIML & other standards: How are concepts handled in AIML?

> http://www.meta-guide.com/home/bibliography/google-scholar/aiml-srai-symbolic-reduction

AIML & SRAI (Symbolic Reduction)

= = =

Note, the following sentences are extracted from the above webpage, reflecting a recent search of Google Scholar:

AIML Symbolic Reduction (SRAI) Technique

AIML is a tail-recursive functional language which is optimized for the semantic processing of strings, where input and output strings are desired to be at the semantic level of sentences in natural language.

The recursive feature of AIML is sometimes called “symbolic reduction” and is abbreviated as “srai” (symbolic reduction artificial intelligence).

This <srai> element can be used to make (a) symbolic reduction, (b) to handling synonyms, (c) to grammatical corrections or (d) to detect key words.

AIML also allows the use of symbolic reduction (SRAI) and wildcards (asterisk “*” and underscore “_”).

The AIML implementation for recursion is the tag <srai>.

The AL-AIML [Affect Listener AIML] set contains 14465 patterns, 15550 response instructions and 6918 srai substitution rules.

The <template> element can be constructed merging more categories together, using the <srai> tag that allows referring to other categories.

Special functions are carried out by the topic, that, and srai tags.

AIML bots support a mechanism for recursive processing via the tag <srai>, which can be instantiated from inside a template.

AIML can also reuse other rules by means of the <srai> tag; however, there is no clear rule structuring since this tag re-launches the evaluation of the whole set of rules for an input reformulation.

Recursive categories have templates including <srai> and <sr> tags, which refer to simply recursive artificial intelligence and symbolic reduction.

A knowledge-base of this kind of chatter-conversational agent is made of pairs of textual/lexical (pattern; template), which can be linked together semantically and/or recursively by means of SRAI connections.

The < srai > tag allows procedures calls and can be used to direct different input patterns to the same exit template.

We started by augmenting the default AIML tag set (including tags such as <srai> and <that>) with two tags: <query>, to seamlessly invoke the core QA module, and <clarify>, to support follow-up detection and resolution.

For instance categories with templates having <srai> or <sr> tags are called recursive categories, which recursively call the pattern matcher to insert the responses from other categories. <srai> and <sr>, which refers to simply recursive artificial intelligence and symbolic reduction are playing critical rules in: reducing complex grammatical forms to simpler ones; splitting an input into two or more subparts, and combines the responses to each; and dealing with synonyms by mapping different ways of saying the same thing to the same reply.

Though posing some risk to novice programmers, we surmised that including <srai> was much simpler than any of the iterative block structured control tags that might have replaced it.

The disagreement over the acronym reflects the variety of applications for <srai> in AIML.

The tag <srai> is designed to recursively find the next pattern.

The <srai> recursion tag is used for several purposes: symbolic reduction; “divide and conquer” (splitting an input into subparts, and combining responses to each of these); finding synonyms; correcting spelling or grammar; and/or conditional branching.

AIML (Artificial Intelligence Markup Language) contains a simple yet powerful XML markup tag called <srai>. The <srai> tag is the symbolic reduction tag. This allows minimalism.

The <srai> tag invokes the recognizer recursively.

But it’s possible that this category may be invoked by another category, using the <srai> tag (not shown) and the principle of reductionism.

[CITATION] Symbolic deduction in Artificial Intelligence Markup Language (AIML) Symbolic Reductions in AIML, by Dr. Richard S. Wallace http://www.alicebot.org/documentation/srai.html

13.13 Recursion, The Anatomy of A.L.I.C.E. http://publication.wilsonwong.me/paper/233282357.pdf

= = =

> http://freemind.sourceforge.net/wiki/index.php/Swing_applications

FreeMind is a Java application written in the Swing graphical toolkit for Java.

> http://en.wikipedia.org/wiki/Swing_(Java)

Swing is the primary Java GUI widget toolkit.

= = =

> http://twitter.com/mendicot/status/252098566418493440

Continuing the conversation about converting sitemaps into outlines, visual mindmaps & ontology trees with @PowerMapper http://goo.gl/5w4sj

News & Events › New chatbots: CHAT BOT JESSICA – [Ext JS + PHP]

> http://twitter.com/mendicot/status/213353542235324417

Ferid, I like your interface, and it does seems to “learn” from what you “teach” it. I get tired of seeing the same “canned” interfaces over and over.

= = =

Okay, I checked it and seems to be working, just a little slow. That’s the way to make a chatbot. Now you have access to as many or more replies as Cleverbot or SimSimi does from its own knowledgebase, and without their overheads.

Development › Tools: ICT Toolkit for Virtual Human

> http://vhtoolkit.ict.usc.edu/index.php/NPCEditor

Non Player Character Editor (NPCEditor) … “contains a text classifier based on cross-language relevance models that selects a character’s response based on the user’s text input, as well as an authoring interface to input and relate questions and answers….”

News & Events › In the news: Program O Version 2.0 in FINAL Beta and we need your HELP!

> http://forum.program-o.com/viewtopic.php?f=18&t=46

Dave, can you tell me anything about the status of the Program O API in Program O 2.0 ?? Is there any documentation available for the Program O API ??

News & Events › New chatbots: Elvis Presley Bot

How come it’s not showing the little HTML5 microphone icon, so I can really talk at it in Chrome19 ? ;^)

And, let’s get our ducks in a row and update the link at http://twitter.com/Elvisbot !

= = =

> http://twitter.com/mendicot/status/210096335637061632

Checking out the all new .. Elvisbot http://talktotheking.com .. “Talk to the King” .. by Ace Craig @elvisbot

= = =

> http://twitter.com/mendicot/status/210099485022494720

@vocaloid_yamaha .. what is the outlook for a ?#NetVocaloid? web API ?

Development › Designing and coding: Nekster / Fb Integration

> http://www.meta-guide.com/jabber-xmpp-chatbots

Jabber, XMPP & Chatbots

> http://www.meta-guide.com/facebook-chatbots-masterlist

Facebook Chatbots Masterlist

= = =

I’ve just made a new Meta Guide webpage all about “Jabber, XMPP & Chatbots” (above). XMPP is one of the best ways to integrate chatbots with almost any other system. Unfortunately, since IMified.com is going out of business, I have been in contact with about a dozen companies trying to arrange an even more user-friendly replacement, virtual plugNplay integration with various social platforms. In Facebook, there seem to be two ways: 1) integrate with Facebook chat via XMPP, or 2) integrate as a Facebook app (plugin).

Development › Platforms: Chatbot SaaS & Web Service Best Practices

> http://en.wikipedia.org/wiki/SaaS

a software delivery model in which software and associated data are centrally hosted on the cloud

> http://en.wikipedia.org/wiki/Web_service

a software system designed to support interoperable machine-to-machine interaction over a network

= = =

I would like to talk a little about what I love and hate in both chatbot software as a service and chatbot web APIs. I’m also keen to hear similar opinions from others. I’ll try not to bash our colleagues by name, but will try to praise them! ;^)

Basically, a chatbot SaaS is a cloud based service that functions more or less the same as it would on the desktop, in terms of GUI. The advantages are that you don’t have to screw around with Windows, Mac or Linux versions, much less bloating hardware issues.

Instead of a “user interface”, a web API is a “programmatic interface”, for instance for machine-to-machine communication in the looming “Internet of Things”. I’m not sure there are good examples of chatbot web APIs yet, at least not well documented or commercial ones. Two of the best sources of information on the role of web APIs in cloud computing are the http://programmableweb.com (@programmableweb) website and the http://gluecon.com (@gluecon) conference.

Development › My Chatbot Project: My learning AI Jay Sim

> http://barc0de.com/

It seems that “Dante – The Language Learning Chatterbot” (above link) is the successor to Leo, and that Alan J. Brown was on Twitter at http://twitter.com/barc0de until late 2010. I believe he is now head developer at http://youthmedia.co.uk .

Development › AIML & other standards: How are concepts handled in AIML?

In my initial attempts using XSLT to map XML sitemaps to MM mindmaps (before even trying to map MM mindmaps to AIML), I hit a few of snags….

1) It’s not clear to me how to translate the directory structure of the URLs in XML sitemaps into the tree structure of MM mindmaps, like one on top of another connected to the following and multiples within.

2) Ideally, a really good sitemap2mindmap translation would also map all internal linkages, which would involve spidering the website then merging all those connections as above.

3) Further, webpage titles are not necessarily included in XML sitemaps; therefore, spidering would also be necessary to extract page titles to include in a better mindmap.

A straight translation from XML sitemap to MM mindmap would probably be inadequate, and so require spidering the whole website beforehand.

Certainly, mapping MM mindmaps to AIML would not be less complex, especially to achieve a minimum of loss of detail.

= = =

> http://twitter.com/topicscape/status/209162374115115009

?@topicscape: @mendicot Don’t know of any way. Prob is, MM mindmaps r tree-based hierarchies, & sitemaps allow connections from any location to any other

> http://twitter.com/roygrubb/status/209162734149963776

?@roygrubb: @mendicot We experimented with importing web sites into Topicscape automatically, and found challenges in dealing with duplication properly

> http://twitter.com/roygrubb/status/209162867851792384

@roygrubb: @mendicot We talked to others who had tried and failed, so we gave up eventually.

= = =

> http://en.wikipedia.org/wiki/OPML

OPML (Outline Processor Markup Language)

= = =

Out driving around in traffic today, a little piece more of this puzzle came to me….

OPML is *Outline* Processor Markup Language. An XML sitemap is an *outline* of a website. And, a MM mindmap is generally an *outline* of ideas. Okay, I’m giving up on the notion of mindmapping internal recursive linkages in within websites; since, apparently MM mindmaps can’t handle recursive linkages – because they are just *outlines*…. I now suspect that using regex one could parse the directory structures in most XML sitemaps, which would result in a type of *outline*. Then one would just have to grab the page titles to make it more useful and esthetic.

Next step, are there any tools available for visualizing AIML KBs as *tree* structures? There must be; I just can’t think of any offhand.

= = =

> http://en.wikipedia.org/wiki/Ontology_(information_science)

an ontology formally represents knowledge as a set of concepts within a domain, and the relationships

> http://en.wikipedia.org/wiki/Outline_(summary)

a list arranged to show hierarchical relationships, and is a type of tree structure

= = =

Can you tell me what the real difference is between an ontology and an outline ?

= = =

> http://websummarizer.com/

WebSummarizer rich visual presentation of interactive summaries

= = =

A little more progress each day….

I’m now consulting with Henry Lewkowicz (@Summarizer), creator of WikiSummarizer and the new WebSummarizer (above), an expert in the conversion of mindmaps. He apparently believes that sitemap2mindmap can be done, with his proprietary processes. However, since he is not familiar with AIML, mindmap2aiml remains to be seen. So again, what tools are available for visualizing AIML KBs as *tree* structures or *outlines* ?

= = =

> http://www.meta-guide.com/home/bibliography/google-scholar/aiml-graphmaster

AIML Graphmaster

= = =

Graphmaster forms the core of the Alicebot engine.

The most important element is the graphmaster which implements the search algorithm that allows the bot to match the user input and construct an appropriate response.

ALICE loads all AIML into a graph metaphor known as a Graphmaster.

AIML categories are stored in a semantic tree named Graphmaster.

The knowledge based in AIML is stored using a mechanism called Graphmaster.

AIML software stores all of the categories in a tree managed by an object called the Graphmaster.

AIML software stores the patterns in a tree structure managed by an object called the Graphmaster, implementing a pattern storage and matching algorithm.

The Graphmaster consists of collection of nodes called Nodemappers.

Graphmaster is a set of files and directories, which has a set of nodes called Nodemappers.

The Graphmaster has a collection of nodes called Nodemapper. Pictorially it is a hierarchy of Nodes, each being either a root, a leaf, or both.

The stimulus-response categories are stored in a tree structure, managed by an object called Graphmaster, implementing a pattern storage and matching algorithm.

This behaviour can be described in terms of the class Graphmaster which has a set of nodes called Nodemappers_ that map branches from each node_ and branches represents the first words of all patterns and for wildcards.

Graphmaster matching is a special case of backtracking, depth-first search. In most cases matching is handled by a linear traversal of the graph from the root to a terminal node.

= = =

BTW, I was recently given a demonstration of machine translation technology. WordNet concepts were represented as numbers, like GUIDs (Globally Unique IDentifier). And, the concepts from over a dozen languages were simply mapped not only between languages but also within a given language via these universal number codes….

= = =

> http://www.meta-guide.com/xml-variants

XML Variants: Bookmarks | Sitemap | OPML | Mindmap | AIML

> http://en.wikipedia.org/wiki/MindManager#File_format

MindManager#File_format

> http://freemind.sourceforge.net/wiki/index.php/Import_and_export#From_MindManager_X5

Import_and_export#From_MindManager_X5

= = =

I have yet to find a real specification for the MM file format. Presumably, the MM file format stands for “MindManager”; however, the MM format used by Freemind does not seem to be identical with the current MindManger file format. I have found an XSL stylesheet (above) that transforms from MindManager into Freemind format. Apparently the real MindManager format involves some kind of ZIP archive nesting containing both XML and binary data. I have made a webpage (above) trying to visually compare these XML Variants.

= = =

> http://www.meta-guide.com/home/bibliography/google-scholar/aiml-templates

AIML Templates

> http://www.meta-guide.com/home/bibliography/google-scholar/aiml-categories

AIML Categories

> http://www.meta-guide.com/home/bibliography/google-scholar/aiml-srai-symbolic-reduction

AIML & SRAI (Symbolic Reduction)

> http://www.meta-guide.com/home/bibliography/google-scholar/aiml-random-tag

AIML Random Tag

= = =

Gary, thanks for your feedback! I don’t have the depth of understanding of the finer points of AIML that you do. I neglected to note that all the sentences in my Graphmaster reply were extracted from the linked Google Scholar page.

I wonder if the “knowledge” doesn’t exist in the *relation* of the pattern to the template, in other words inside the category. So in terms of classification, the patterns could be seen as a reverse tree (roots) of the templates?

The “symbolic reduction” of the SRAI tag would seem to provide at least a partial answer to my original question about how concepts are handled in AIML. Can we say that SRAI functions or defacto SRAI structures form a kind of ontology, or ontologization? And conceptually, how does the randomization fit in the bigger picture? Doesn’t randomization just expand the tree “roots”? It has been noted to provide more “humanness”.

= = =

> http://twitter.com/mendicot/status/207492128035708928

PORDL http://pordl.com .. ?#XSLT? web feed transformer, ?#XSL? to HTML .. by ‘web programmer guy’ @smailliwnosaj

> http://pordl.com/transform.aspx?id=539

Nested List SiteMap from a Flat XML File

> http://pordl.com/xsl/539.xsl

Nested List SiteMap XSL stylesheet

= = =

It seems ‘web programmer guy’ Jason Williams has not only provided at least a partial solution for how to parse an XML sitemap into an outline something like OPML, but also a web service for at least partial schema translation, at Pordl.com . I haven’t been able to find anything else even close, and some experts said it couldn’t be done.

Just to put this in context, the basic idea is for AIML chatbots to not only “read” mindmaps, but also sitemaps in order to potentially discover conceptual relations, and further “understanding”. Whether this will eventually prove possible or practical is anyone’s guess. Theoretically, it would seem to provide a potential alternative to conventional web semantics.

= = =

http://en.wikipedia.org/wiki/Topic_Maps

>> Topic Maps are similar to concept maps and mind maps in many respects, though only Topic Maps are standardized. Topic Maps are a form of semantic web technology, and some work has been undertaken on interoperability between the W3C’s RDF/OWL/SPARQL family of semantic web standards and the ISO’s family of Topic Maps standards. <<

= = =

http://maiana.topicmapslab.de/

>>Maiana is the most efficient service to host, explore and share Topic Maps sources.<<

http://projects.topicmapslab.de/projects/maiana/wiki/API_Controller

>>The API is awaiting your calls at http://maiana.topicmapslab.de/api and is able to process a JSON object.<<

http://onotoa.topicmapslab.de/

>>Onotoa is an Eclipse-based ontology editor for Topic Maps.<<

= = =

So far, I haven’t found any converter from mindmap into topicmap. Topicmap sounds like a great idea, but actually the number of users of topicmaps is miniscule compared with mindmaps. Theoretically, topicmaps seem to be more compatible with ontologies than mindmaps.

Okay, maybe it’s not necessary to mindmap the AIML itself; that was just one way to try to conceptually reverse engineer the process. All that would be necessary would be to auto-convert mindmaps into AIML. So, the recursive “symbolic reduction” of the SRAI tag could be key here?

From what I’ve heard, it seems Richard Wallace will be adding some new tags to AIML in order to better accommodate web semantics.

Development › Designing and coding: New Approach To AI

> http://www.youtube.com/watch?v=g35o62nlOEM

Event Driven Business Architecture

> http://www.youtube.com/watch?v=F7vLKXkMQow

What is Enterprise Messaging?

= = =

Here are two videos that explain relatively simply Event-driven Architecture and Message-oriented Middleware. What I got out of the message-oriented middleware is that it is not GUI middleware, as I tend to think of middleware, but rather “message-oriented”; in other words, the middleware actually consists of messaging rather than GUI. One might even say that message-oriented middleware is more like command-line middleware.

I might add that one of the beauties of the modular API model is that APIs can all be written in different languages, but the API functionality is in effect language-agnostic, which then can be more easily integrated with middleware, IDEs or frameworks.

= = =

> http://www.meta-guide.com/home/open-chatbot-standards

Robert, have you seen my recent videos on “Open Chatbot Standards for a Modular Chatbot Framework”, above? I’m trying to encourage everyone to build web APIs, as commercial, meterable “modules” in the form of programmatic interfaces to conventional web services.

Apparently, Karsten Fluegge of Pannous.com, creator of the Jeannie Android app, has also created something like generic API access for agents related to his Voice Actions app. I believe Richard Wallace has written something about it on his new “Answer Devices Blog”, below and including documentation, below2.

> http://www.answerdevices.com/index.php?/blog/1/entry-1-pannous-launches-web-service-to-aid-mobile-assistants/

> https://docs.google.com/document/d/1dVG_B5Sc2x-fi1pN6iJJjfF1bJY6KEFzUqjOb8NsntI/edit

Development › AIML & other standards: How are concepts handled in AIML?

> http://www.chatbots.org/ai_zone/viewthread/840/

Uchiha has got me thinking about whether or not AIML chatbots could read MM mindmaps, and if so whether or not it would be useful…. So, how are concepts handled in AIML? I know there have been various attempts to connect AIML chatbots with WordNet, for instance. How is this done, and is it really useful?? The whole issue of concepts ultimately relates to the semantic web technologies and their integration with AIML, which I know people are working on at the moment….

= = =

> http://www.aihub.org/pdf/04338340.pdf

Sub-Symbolic Semantic Layer in Cyc for Intuitive Chat-Bots (2007)

“ALICE-based chat-bots have been provided with advanced reasoning capabilities through the linking of the AIML interpreter with the OpenCyc commonsense ontology.”

= = =

> http://www.daxtron.com/pdf/CYN_Description.pdf

Living in cyn: mating aiml and cyc together with program n (2004)

“Daxtron Labs’ experiments on linking the Artificial Intelligence Markup Language (AIML) interpreter called Program N (by Gary Debuque) to OpenCyc (a freeware version of the Cyc program created by Cycorp).”

= = =

> http://programw.sourceforge.net/

“Program W is an AIML interpreter written in Java. It extends Program D technology with new AIML tags that allow chatbots to query the WordNet lexical dictionary. Chatbots can use information about lexical terms and evaluate existing relations between words.”

Apparently the creator of ProgramW (above), Alessandro Caronia, co-wrote a 2009 paper about it, “A semantic layer on semi-structured data sources for intuitive chatbots”; but, I can’t seem to find a copy available online.

I did find a copy of a 2012 paper by Caronia’s colleagues, Giovanni Pilato etc., “A Modular System Oriented to the Design of Versatile Knowledge Bases for Chatbots” http://bit.ly/LxCBvP , which mentions AIML quite a bit.

Thanks for the helpful reply Dave!

= = =

> http://www.meta-guide.com/home/bibliography/google-scholar/aiml-opencyc

AIML & OpenCyc

> http://www.meta-guide.com/home/bibliography/google-scholar/aiml-wordnet

AIML & WordNet

> http://www.meta-guide.com/home/bibliography/google-scholar/aiml-ontologies

AIML & Ontologies

= = =

Basically, OpenCyc is an ontology. WordNet can serve as an ontology. Mindmaps are also a form of ontology.

So, AIML should be able to use mindmaps in a similar way to OpenCyc and WordNet….

Let’s ask the question in another way….

How could MM mindmaps be made from AIML KBs, or rather how can we mindmap AIML ??

= = =

> http://en.wikipedia.org/wiki/XSLT

AIML is an XML variant, a markup language.

The mindmap MM file format is also an XML variant, another markup language.

We know that XSLT is a good way to transform virtually any XML variant into another.

Hmmm …

= = =

> http://en.wikipedia.org/wiki/FreeMind

FreeMind is a free mind mapping application written in Java.

> http://freemind.sourceforge.net/wiki/index.php/Export_using_XSLT

There is a function that allows exporting of FreeMind mind map using any XSLT—a transformation stylesheet. Several transformation stylesheets come as part of FreeMind distribution, located in the “accessories” subfolder.

> mm2opml.xsl – to OMPL

> opml2mm.xsl – from OPML

= = =

This is a little progress. Freemind at least allows exporting via XSLT, and comes with an XSL stylesheet for converting to OPML. There is also a stylesheet for converting from OPML to mindmap. I’m not sure if Freemind also imports via XSLT. And, it would take some testing to find out if there was any loss of detail going either way.

What this means is that if AIML could be converted into or out of OPML in any meaningful way, without too much loss of detail or functionality, then there would be an avenue for going back and forth between AIML and mindmap.

Presumably, by designing better XSL stylesheets then the OPML step could be eliminated altogether, allowing transformation directly from MM to AIML and back, but will require some concentrated, if not painstaking work to accomplish.

Basically, if we can figure out the correct XSL stylesheet configurations, then we could get AIML to talk to mindmaps and vice versa, theoretically at least!

= = =

> http://www.quora.com/XSLT/Is-there-any-high-performance-XSLT-web-service-available-for-realtime-schema-translation

Is there any high performance XSLT web service available for realtime schema translation?

I’m particularly interested in going from XML sitemap <=> MM mindmap <=> AIML (Artificial Intelligence Markup Language), in other words translating website sitemaps into mindmaps then making them ontologically available to dialog systems.

= = =

> http://twitter.com/mendicot/status/207528165864775680

Testing new webpage2mindmap summarizer .. Web Summarizer http://websummarizer.com for http://twitter.com/Summarizer .. creator of http://twitter.com/WikiSummarizer .. ?#mindmap?

= = =

Hi Hans Peter,

Good one, I didn’t know about VUE. I’m not sure where this will lead either, but somehow it seems related to integrating semantic web technologies with AIML….

I think that this is about hybrid visual and automated solutions. Maybe it’s about bypassing semantic web technologies and discovering another way….

I don’t know of good tools for either visualizing AIML KBs or visually editing AIML KBs. I don’t know of good tools for visualizing the automated processes in realtime.

There is a lot of human effort going into making things like mindmaps, as well as tools like VUE. Beyond that there is an immense store of website structures in the form of sitemaps, which also represent a kind of ontology.

The idea would seem to be, how could AIML dialog systems access and leverage this immense trove of relations, in mindmaps and sitemaps? (Relations not even coded into RDF yet….)

So, the questions seem to be how could AIML read MM mindmaps, and how could MM mindmaps read XML sitemaps??

Ultimately, will we really need RDF, yet another markup language, but containing additional ontological metadata coded into microformats?

Maybe you can tell me? ;^)

= = =

> http://www.meta-guide.com/home/bibliography/google-scholar/ontology-alignment-dialog-systems

Ontology Alignment & Dialog Systems

= = =

“Ontology alignment, or ontology matching, is the process of determining correspondences between concepts.” (On Wikipedia, “ontology mapping” defaults to “semantic integration”.)

“The problem of Ontology Alignment has been tackled recently by trying to compute matching first and mapping (based on the matching) in an automatic fashion. Systems like DSSim, X-SOM or COMA++ obtained at the moment very high precision and recall.”

http://en.wikipedia.org/wiki/DSSim http://kid.dei.polimi.it/index.php/X-SOM http://dbs.uni-leipzig.de/Research/coma.html

Looking at these systems, the first thing that strikes me is how similar they are to XSLT systems….

Development › Designing and coding: New Approach To AI

> http://www.meta-guide.com/home/bibliography/google-scholar/concept-mapping-dialog-systems

Concept Mapping & Dialog Systems

Uchiha, I’ve decided this is an intriguing premise…. Could chatbots read mindmaps, and if so would it be useful??

I didn’t find a specification for the MM file format, but know its an XML variant.

For instance, AIML is also an XML variant, and we know chatbots are fine with AIML.

It’s relatively straightforward to translate between XML variants with XSLT.

So, if we had an MM interpreter for AIML chatbots, what would it tell us?

Responses are coded into AIML; but, mindmaps usually only contain concept relations.

Mindmaps are basically tree structures. Lots of NLP programs traverse tree structures.

So, how would specific AIML responses physically associate with the mindmap concept tree?

= = =

> http://www.meta-guide.com/home/bibliography/google-scholar/uml-unified-modeling-language-dialog-systems

UML (Unified Modeling Language) & Dialog Systems

> http://www.meta-guide.com/home/bibliography/google-scholar/language-modeling-dialog-systems-2011

Language Modeling & Dialog Systems 2011

= = =

Uchiha, it does seem that UML is perhaps associated with dialog systems even more than concept maps, or mind maps for that matter. UML would also seem to be more in line with Wolfram SystemModeler.

However, this brings us from “visualizing” to “modeling”. There seem to be at least two different kinds of modeling associated with dialog systems. UML would represent a kind of physical modeling; whereas, there is also statistical or probabilistic language modeling. And, there seem to be quite a few tools associated with language modeling and dialog systems.

This is an interesting tangent for me; as, it relates to my theories about the “clutch” or transducer mechanisms involved in the conversion of words to images, and images to words in the human brain/mind. Might not there be some connection between this “physical” modeling and the linguistic modeling ??

And, how might sitemaps and/or mindmaps assist with this physical/visual or linguistic modeling ??

Modeling => Language

Language => Modeling

= = =

> http://www.google.com/search?q=modeling&tbs=dfn:1

The art or activity of making three-dimensional models

The devising or use of abstract or mathematical models

> http://www.meta-guide.com/home/bibliography/google-scholar/statistical-package-dialog-systems

Statistical Packages & Dialog Systems

> http://www.meta-guide.com/home/bibliography/google-scholar/mathematica-dialog-systems

Mathematica & Dialog Systems

= = =

According to Google’s definition of modeling, math ought to mediate between the visual and the linguistic….

visual <=> math <=> linguistic

This would be in line with the Mathematica software behind most Wolfram products.

Basically, we may be looking at math mediated conversions between words and images, and vice versa….

Uchiha, I’m a practical person. I actually don’t like the fact that too many people entering this arena try to reinvent the wheel from scratch…. I recommend thinking about practical tools. I believe the most practical tools today are web APIs, at least for me. So, think about which piece of the puzzle most interests you, then try to provide a solution by making a tool (API) for that process, which everyone else might be able to build upon, and could even make you some money…. See my recent videos on “Open Chatbot Standards for a Modular Chatbot Framework” => http://www.meta-guide.com/home/open-chatbot-standards .

= = =

> http://www.meta-guide.com/home/application-programming-interfaces

Application Programming Interfaces (APIs)

> http://www.meta-guide.com/home/artificial-intelligence-middleware

Artificial Intelligence Middleware

> http://www.meta-guide.com/home/bibliography/google-scholar/protege-ontology-editor-dialog-systems

Protégé Ontology Editor & Dialog Systems

> http://www.meta-guide.com/home/bibliography/google-scholar/eclipse-ide-dialog-systems

Eclipse IDE & Dialog Systems

= = =

There should always be balance between the macro and micro levels; don’t get lost in either. Just work on a few modules that you care most about. Then mix and match with other people’s modules (APIs) to achieve your desired functionality. The way to integrate APIs is with middleware, IDEs, or frameworks. Myself I’m focussing on cloud based middleware, IDEs, and frameworks – PaaS & IaaS, for distributed multi-agent systems based on Grid computing.

Probably, Protégé and Eclipse are the two most popular high level frameworks for dialog systems. Protégé is twice as popular as Eclipse. I have yet to find any cloud services offering either Protégé or Eclipse, much less any reasonable substitutes in the cloud….

= = =

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

g-Eclipse Project – Tools for Cloud and Grid Computing

> http://www.meta-guide.com/home/bibliography/google-scholar/emi-european-middleware-initiative-glite

EMI (European Middleware Initiative) & gLite (Lightweight Middleware for Grid Computing)

= = =

Uchiha, you got me motivated to dig a little deeper into this particular mystery…. There seem to be two European funded projects, g-Eclipse and EMI (formerly gLite). g-Eclipse “aims to build an integrated workbench framework to access the power of existing Grid infrastructures”. And, the European Middleware Initiative “aims to deliver a consolidated set of middleware products based on the four major middleware providers in Europe”, now incorporating gLite into its EMI 2 Matterhorn product. EMI has videos online at => http://www.youtube.com/user/emieurope/videos .

= = =

> http://www.meta-guide.com/home/bibliography/google-scholar/stomp-simple-text-oriented-message-protocol

STOMP (Simple Text Oriented Message Protocol)

= = =

Hans Peter, I’m definitely interested in learning more about what you are doing with your ‘strong-AI engine’ http://mindconstruct.com , as well as about how you are doing it. I’m a strong believer that there should always be balance between the macro and micro levels, not to get lost in either. I think you’re on the right track developing for the “Internet of Things”.

STOMP is used in message-oriented middleware for event-driven architecture. Would you say it’s comparable to OpenJMS (Java Message Service) used in UIMA (Unstructured Information Management Architecture) for IBM Watson? How did you finally decide on STOMP?

= = =

> http://www.youtube.com/watch?v=VgNk-VLVPvc

Henry Markram: The Origins of the Human Mind

= = =

This is a cool new Henry Markram video, where he talks about the geometries of modeling within the human brain (starting at 3:40), in the context of the European Human Brain Project http://humanbrainproject.eu .

= = =

Uchiha, you’ve been doing okay so far, and gave me some good ideas! Nobody knows it all, otherwise it would have already been done. We’re also reaching the limits of my knowledge. I had to do some new research to find out about gEclipse and EMI. What I’ve really gotten out of this thread was the geometric mediation of the words to images, and images to words conversions; and, it seems Henry Markram at least was already aware of that.

C++ is a good language to proceed with. I’m working on a webpage of C++ resources in AI and NLP, and will let you know when that’s ready. I’m not a great programmer myself, which is why I’m always looking for tools to help me. If I were you, I would start getting any C++ dialog system (chatbot) actually working. AIML is as good a place to start as any. At least by the time you reach the limits of AIML, you will have a much better idea of what’s involved. That said, there’s an awful lot that can be done with AIML; I’m not even sure the limits have been reached there. I sincerely believe that for 95% of the people in the world something like the AIML Superbot is all they will ever need, in terms of dialog system.

Hans Peter, that was a great reply about your STOMP journey, and I look forward to reading your whole blog. Just settling on which programming language, much less which messaging protocol is already great progress. I love the way your website lists your hardware platform, as well as the solution stack. And, I’ll quote you on that, “simplicity is more scalable than complexity”…. ;^)

Development › My Chatbot Project: New Website: empathynow.com

Hi Mohan, I’ve often found that “roughing-out” in stages is the best way to move forward complex, long term projects a bit at a time. I have to say that I’m becoming an even bigger fan of APIs than I am of GUIs. APIs will be easier to hook-up with speech technologies and voice platforms. I still think that audio-visual Skype chatbots will prove more cost effective than other avatar platforms, in terms of reach. You’ve got a good angle, work it!

General › New here? And general stuff: Chatbots Without Borders

> http://twitter.com/erwinvanlun/status/205681769436028929

@erwinvanlun: I expect ?#voicetechnology? will be a big solution for illiteracy in Pakistan! A HUGE opportunity for commercial parties through ?#brandagents?

> http://twitter.com/mendicot/status/206026185640116224

@mendicot: @erwinvanlun .. re ?#voicetechnology? for ?#development? .. see ?#mvoices? http://mvoices.eu by http://twitter.com/webfoundation .. as well as http://twitter.com/awaazde ..

= = =

So, what is the right moment to begin a modest philanthropic project for “Chatbots Without Borders”? ;^) Anyone care to brainstorm?

= = =

> http://twitter.com/mendicot/status/236853734691463168

Watching video .. Smart Phone Farming (in Africa) http://youtu.be/egSjewfJyIw .. related to @kuzadoc SMS by @backpackfarm @mercycorps & @sawbosm ..

= = =

> http://twitter.com/mendicot/status/258230342077538304

Reading @anilkumarsastry .. ‘speaking’ machine designed to help the illiterate http://goo.gl/UFB9J .. includes biometric finger print reader

Development › Designing and coding: Programmatic access to RiveScript’s guts

> https://code.google.com/p/rivescript-cpp/

Noah, is there any RiveScript Interpreter for C++ ?

Development › Designing and coding: A Better AIML-to-RiveScript Converter

> http://www.verbots.com/wiki/Tools:AIML_to_Verbot_Converter

Hi Noah, this reminds me of the “AIML to Verbot Converter” (above). I’ve found that lots of conversions can be made using XSLT (below). For instance, with XSLT I was able to convert back from Verbot-to-AIML. There are some good XSLT programs, but they can be expensive. I’ve also found some web services that can handle XSLT. There are imperfections in conversions with XSLT, some functionality may be lost each way, mainly due to differences in tags and positions between languages.

> http://en.wikipedia.org/wiki/XSLT

Development › AIML & other standards: CallMom

> http://twitter.com/mendicot/status/230076137366237184

Sweet, just unboxed my new #Nexus7 tablet .. and already talking with @MitsukuChatbot on @Pandorabots CallMom Beta http://bit.ly/Jl22ka ..

= = =

> http://www.meta-guide.com/home-automation

I’ve got a Meta Guide webpage full of resources for “Dialog Systems in Smart Home Automation & Domotics (Domestic Robotics)”, above.

> http://www.chatbots.org/ai_zone/viewthread/1001/

One of the issues with AIML and Pandorabots is the absence of a good “middleware” for integrating APIs; I’m currently looking into iPaaS, or integration PaaS.

> http://research.microsoft.com/en-us/projects/homeos/

You might have a look at the new Microsoft HomeOS, Microsoft Robotics Developer Studio, and Kinect for Windows, which has speech capabilities.

> http://ifttt.com/channels

IFTTT is an interesting new service with an increasing number of easy integrations for realworld devices, such as WeMo, as well as with mobile such as Pushover, facilitating the promised Internet of Things.

> http://twitter.com/mendicot/status/228171192052379648

There are other new services similar to IFTTT specifically for mobile, such as Triggers http://whatgoesin.com & on{X} http://onx.ms (from Microsoft Israel, and so may play well with HomeOS).

General › AI thoughts: Is it possible to generate knowledge within the knowledgebase?

I’ve read about bots that have implemented a “dreaming” phase for processing information during downtime.

I do know that Ultra Hal on Twitter http://twitter.com/UltraHal is always learning from conversations on Twitter without participating in them.

= = =

IBM Watson would be an example of “internal”, and I believe they had to do a tremendous amount of “pre-processing” to create knowledge from data. Whereas, Apple Siri might be an example of “external”, where there is supposedly crowd-sourced cloud-learning happening all the time.

The Zabaware Ultra Hal Assistant, by Robert Medeksza, has a “Dream Machine” plugin called “Dream Out Loud” that enables “talking dream mode”. Apparently, “it keeps track of the topics you talk about then at some idle point will look up those topics and find sentences and or phrases about that topic and will use them to talk to itself” (sort of a sub-conscious).

Someone has actually taken out a patent on “robot dreams” (see below link), but when I contacted them about it got no reply.

=> http://www.meta-guide.com/home/bibliography/google-scholar/robot-dreams

Vinu Arumugham (link below) has created FemtoThnk (below 2), a cybernetic behavioral model that features higher level brain functions that include a version of dreaming.

=> http://home.comcast.net/~vinucube/femtothnk.html => http://sourceforge.net/projects/femtothnk/

And another more recent example (below) from the “HARUMI project”.

=> http://jeffelson.e-monsite.com/

>>When Harumi is not sollicited by user for more than 10 minutes, she will start to “dream”, meaning she will explore randomly answers available in her database then put back those answers as stimulus if they contain a word non present in entries. This means that she’ll restructure by herself the organisation of her memory in order to be more efficient.<<

= = =

BTW, I’ve never really liked the term “chatterbots”, though it was certainly an apt description of a generation of conversational agents; however, in the immediate future I expect bots to be more practical, task oriented, and useful to people, hence the current term “assistant”. For this reason, I’ve always felt that the Turing test was a red herring. We don’t need bots that can fool people; we need bots that can help people, along the lines of augmented intelligence.

= = =

Victor, the statistical confidence scoring of IBM Watson would take care of this accuracy issue; and, there are already APIs in the pipeline that could make that kind of statistical confidence scoring available to “street level botmasters”. ;^)

I certainly want bots (assistants) that are much smarter than people. ;^) See my recent Quora answer to, “How would a society benefit from an AI that passes the Turing test?”:

=> http://www.quora.com/Artificial-Intelligence/How-would-a-society-benefit-from-an-AI-that-passes-the-Turing-test/answer/Marcus-L-Endicott

Development › AIML & other standards: CallMom

> http://en.wikipedia.org/wiki/Android_version_history

> http://www.quora.com/Android-Applications/Can-Android-2-x-phone-apps-be-used-on-Android-3-x-and-4-x-tablets

Since I’m on iPod Touch, I don’t need another pocket device, so am thinking about getting a new Android tablet for testing CallMom. Samsung Galaxy wifi-only mini-tablets look interesting (no plan required, as with iPod Touch). Most Android tablets seem to be running Honeycomb or Ice Cream Sandwich (see version history above). I asked the question on Quora (above 2) about upward compatibility, which was answered theoretically affirmative.

Before I buy, I would just like to know if anyone has tried CallMom on an Android tablet and has it actually working ??

General › New here? And general stuff: Slide Agent Demo Now Online!

It was not immediately clear to me that the “slide agent” was under the purple tab. I visited all the pages a number of times looking for it. 😐 BTW, I really don’t care for the repeat name confirmation; I got caught in a loop.

News & Events › New chatbots: we are launching a new chatbot after easter

> http://en.wikipedia.org/wiki/Tania_Peitzker

Hi Tania, I read about you on Wikipedia, cool.. And, I’m now following you on Twitter, at @PeitzkerTania.. (I couldn’t find anything on Twitter for @myownreporter..)

> http://www.youtube.com/watch?v=X5BSzGM_mko

I’m watching your demo video now; but, can you tell us anything more about what “powered by velmai” means? This reminds me of some work Tom Joyce (8pla.net) has done with robot reporters, see his demo video at http://www.youtube.com/watch?v=FD3Ibuh-iMM ..

I’m Australian-American, born in Melbourne of American parents.. I’m in the States this year, but may come back to Oz next year.. BTW, I’ve just returned from presenting at the Chatbots 3.2 conference in Philadelphia..

= = =

> http://emm.newsbrief.eu/overview.html

Not long ago I read about the Europe Media Monitor “intelligent news event extraction system”, by EMM Labs http://emm-labs.jrc.it .. Is this related to the “velmai” or “velmais” you’re referring to ??

= = =

> http://www.youtube.com/user/fruitcakedesign

The only reference I can find for VELMAI LTD (velmai.com) points to Cliff Lee at http://fruitcakedesign.com ..

Development › My Chatbot Project: WinAlice

Where is this latest version of WinAlice available?

The current AIML PHP action seems to be at http://www.program-o.com .

At the moment, the best AIML Windows speech integration seems to be http://www.guile3d.com .

Development › Tools: Mindmapping Knowledgebases

> http://en.wikipedia.org/wiki/List_of_concept_mapping_and_mind_mapping_software

What are some useful tools for visualizing knowledgebases? For instance, are there any visual editors for AIML (or ChatScript)?

Mindmapping seems to be a useful way to visualize tree structures. It would be great to have a conversion tool for AIML into Freemind, or Freeplane, format. Freemind format is basically another XML variant, so XSLT could be used for conversion.

> http://www.meta-guide.com/home/mindmap

I’ve recently tried converting my Meta Guide website sitemap into mindmap format, and was surprised to find no easy import tool available for converting sitemaps into mindmaps. I can see no real difference between visual sitemaps and mindmaps, just basic tree structures.

= = =

> http://www.ai-forum.org/topic.asp?forum_id=1&topic_id=72481

What would be really grand is a convenient way to *visualize* the knowledgebase, and both visually edit and speech edit, in other words visually explore the knowledgebase and then input answers or replies using speech-to-text….

= = =

> http://twitter.com/mendicot/status/252101151665819648

Meta Guide webpage aggregating conversation around converting sitemaps into outlines, visual mindmaps & ontology trees http://goo.gl/oypT3

= = =

> http://www.meta-guide.com/mindmap-conversion

As of today, I have successfully converted from Sitemap to Mindmap, via Bookmarks.

> http://www.meta-guide.com/home/mindmap

Sitemap => Yahoo! Pipes => Spreadsheet => IE => Freeplane

= = =

And, they said it couldn’t be done…. ;^)

= = =

Next step…. So then I googled “aiml”+“csv”+conversion, haha.

> http://www.google.com/search?q=“aiml”+“csv”+conversion

Kino Coursey’s work with CyN came up first.

> http://www.chatbots.org/ai_zone/viewthread/794/

But second was Dave Morton’s work! ;^)

= = =

According to the immense artificial intelligence behind Google, Dave Morton should be the number two expert in the world on AIML-CSV conversion…. ;^)

We know that AIML contains recursive linkages, as do websites; therefore, hierarchical outlines, such as mindmaps, can be but imperfect reflections.

However, it is still possible to represent many if not most websites as hierarchical outlines, or mindmaps.

Is it then still possible, or reasonable, to attempt to represent AIML in hierarchical outlines, or mindmaps?

Dave, is there any software utility or web service available for the convenient conversion of AIML into or out of CSV??

And, what is the relationship of spreadsheets to relational databases, such as MySQL?

> http://www.meta-guide.com/home/about/videography/best-spreadsheet-database-videos

Would relational databases be better than spreadsheets for automating this kind of conversion?

Can we, or should we, attempt to represent AIML knowledgebases visually in the form of mindmaps??

I happen to think that such a visual AIML editor, even a collaborative, online visual editor (such as Mindmeister for mindmaps) could be beneficial….

= = =

For example, here is a hierarchical view of an AIML file using the XPath HTML5 parser in Yahoo! Pipes….

= = =

So, what would a chatbot look like that derived knowledge from sitemaps and/or mindmaps?

The idea would be to produce natural language replies using the ontological “knowledge” represented in the sitemaps/mindmaps. It could be tested using 1, 10, and 100 sitemaps/mindmaps. If using 100 didn’t produce gobbledegook, then it could be tried using 1,000 etc sitemaps/mindmaps.

The issue with using sitemaps in this unconventional way is the nesting. It should be noted that not all websites are based on directory structures; some, larger websites are data-based (based on databases). Once sitemaps are nested, based on directory structure, then they can be made available as hierarchical outlines (trees), to mindmaps for instance.

Mindmaps have been primarily a GUI for human use. Making mindmaps available to machines would involve resolving and aligning the nesting issues both of mindmaps and AIML. Mindmaps and AIML are both XML variants, but unconventional XML variants, due to peculiar nested relations. It should be noted that due to the recursion in both websites and AIML that machine written, automated AIML would necessarily be inferior to human, hand written AIML.

Probably, such an experimental chatbot would require a partial “stock” or base personality, and be able to make “inferences” or interpretations based on the ontological “knowledge” represented in the sitemaps/mindmaps. I can imagine starting with agricultural sitemaps/mindmaps, and querying the chatbot about milk for instance.

Development › Designing and coding: What are the tools and methodology to “make bot understand”

The place to start is AIML. Once you understand how AIML works, and can get it working the way you want then you’re ready to move on to other methods. ChatterBean and Program D are Java AIML interpreters. It might be a good project to see if you can get either one working on Google App Engine. If you do, publish a blog post about it, because others will be interested in how you did it.

Pattern matching AI is not much different from data mining and sentiment analysis. So, the next step would probably be to go with the popular Python NLTK Natural Language Toolkit. Grammar parsing gets into shaky ground; because, there is no one right way to parse, or “understand”, natural language. For instance, IBM Watson uses lots of different techniques in parallel, and then correlates all the results statistically, or probabilistically.

The ultimate challenge today is working with semantic web data such as RDF, and being able to interact effectively with it in natural language. For instance, IBM Watson uses structured data, such as triplestores, in order to figure out, or “understand”, parallel unstructured text.

News & Events › Events: Chatbots 3.2 Conference – Philadelphia March 31, 2012

> http://twitter.com/search/#Chatbots32

I’m still in Philly this morning, but flying out in the afternoon.. See my #Chatbots32 tweets (above link).. (Note, I only tweeted about peeps already on Twitter..) It was indeed amazing and gratifying to meet Dave, Steve, Richard, and others in person.. I’m already looking forward to the next opportunity.. ;^)

News & Events › New chatbots: Harumi

Jean-François, what is “RSS flux”? It seems to be something French. I could only find this definition: “RSS flux is a text file whose content is produced automatically based on information that is updated and published on a website.” It seems you are doing what I would like to do. I work with web feeds a lot. Have you seen my project at http://meta-guide.com ?

= = =

> http://en.wikipedia.org/wiki/Web_feed

I suspect that “flux” means “feed” in French. Can you confirm that you are working with standard RSS XML (above) ? If so, I’m very interested in how you are parsing it to NLP. What AI engine are you using, pattern matching ?

= = =

> http://www.meta-guide.com/home/knowledgebase/best-rapidminer-videos

Best RapidMiner Videos

= = =

HP, that’s a hot tip, thanks! I’ve installed RapidMiner on my new machine, and will let you know how it goes. I’ve made a webpage above on “Best RapidMiner Videos”, which also includes tutorials.

Development › Designing and coding: New Approach To AI

> http://www.meta-guide.com/home/bibliography/google-scholar/tasks-of-natural-language-processing

Tasks Of Natural Language Processing

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

Modules / Modular Programming

> http://www.meta-guide.com/home/application-programming-interfaces

Application Programming Interfaces (APIs)

> http://www.meta-guide.com/home/artificial-intelligence-middleware

Artificial Intelligence Middleware

> http://www.meta-guide.com/home/open-chatbot-standards

Open Chatbot Standards for a Modular Chatbot Framework

= = =

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

Computational metaphorics concerns the study of metaphor analytics.

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

A number of basic computational models for dreaming have been proposed. Very likely metaphor analysis will prove to be the bridge between natural language technology as we know it today and the realistic brain functionality of tomorrow.

> http://www.quora.com/Linguistics/Is-it-possible-to-explain-metaphors-using-discourse-analysis-frameworks-or-only-with-cognitive-linguistic-frameworks

Is it possible to explain metaphors using discourse analysis frameworks, or only with cognitive linguistic frameworks?

= = =

> http://twitter.com/mendicot/status/206776160447770625

@Wolfram_Alpha .. re ?#SystemModeler? => would like to point at XML ?#sitemap? and get MM ?#mindmap? back ..

==>> http://www.wolfram.com/system-modeler/

Development › Platforms: Skype versus Avatar platform

I’ve been racking my brain for quite some time trying to hit on the ideal avatar platform.

However, I’m concluding that Skype, or any VoIP videoconferencing platform, would be best.

Does anyone have Denise or Ultra Hal configured for incoming Skype calls? If so, I’d love to check it out!

Who needs to deploy a mobile app, or even web app, when you can just Skype the chatbot? I would love to hear from anyone with experience doing this!

= = =

Hi Laura, the interesting thing about the Skype option is that ANYONE from ANY mobile or desktop could call an agent via VoIP videoconferencing, with fully interactive voice and realistic video animation. I simply want to Skype my agent from my mobile, or desktop, see a realistic animation, and fully interact via voice, just as I would with any person. (If I could tell my agent to Skype someone else, for whatever reason, so much the better.)

Now, if I can just figure out how to run this fully in the cloud, and access the backend via some kind of remote desktop software, then I’ll be set! ;^)

= = =

Merlin, firstly who actually has a great (open) avatar interface for the web? Not SitePal at $40 per month.. AFAIK, there is no decent (open) avatar interface for iOS at any rate.. The beauty of the Skype workaround is that it does away with the necessity for mobile and web apps completely.. Remember, we are talking multimodal agent here, fully voice interactive and realistically embodied..

This can in fact be done using Guile3d Denise, with the addition of the ManyCam.com product, however not yet with remote cloud hosting (PaaS)..

= = =

> http://www.livingactor.com/

Merlin provided a good summary of the current options. Cantoche provides another option, “Living Actor Presenter” (used by Jason Yosinski etc. for their viral video, “AI vs. AI. Two chatbots talking”); but, I believe its also pricey on par with SitePal.

Erwin, what you have listed under Skype is for IM. There is a tremendous amount of confusion about this all over the net in regard to chatbots. Since chatbots are primarily textual, and so eminently compatible with XMPP, this naturally jumps into people’s minds first.

I think Jan gets it, and is quite right on the integration point as one true drawback. People do complain a lot about the Siri clones not being able to do the deep OS manipulations that Siri can.

= = =

> http://en.wikipedia.org/wiki/Softcam

A softcam is essentially a software-based camera.

> http://www.meta-guide.com/home/about/videography/100-best-manycam-videos

I’ve been digging a little deeper into “softcams”, like ManyCam, and how people are using them for instance on ChatRoulette….

> http://www.meta-guide.com/home/about/videography/100-best-chatroulette-tutorial-videos

= = =

Forget the web, forget apps… Skype is available on virtually any platform. People video conference with each other using Skype etc. Why not solve the avatar problem universally? Apparently anything that can run on your desktop can be routed into Skype via softcam.

The most “user friendly” avatar platform I’ve found is Second Life; so, I’m wondering if there is not some way to Skype (voice and video) interactively with a Second Life NPC avatar via softcam….

> http://www.quora.com/Second-Life/Can-a-Second-Life-avatar-be-displayed-interactively-on-a-website-or-in-a-mobile-app

General › AI thoughts: Sparking Together

> http://www.sparkingtogether.com/

Does anyone have a clue what this new “Sparking Together” initiative, apparently from Adele Robots (AdeleRobots.com), is all about ??

They’ve got Twitter, Facebook, and some really wacky videos on YouTube ..

> http://twitter.com/Sparking2gether

> http://www.facebook.com/pages/Sparking-Together/180513272042574

> http://www.youtube.com/user/SparkingTogether

They seem to be trying to pull together some kind of new robot community ..

This reminds me of the recent “Project Aigo” from Peter Voss of AdaptiveAI.com to solicit volunteers to help build up their domain specific knowledgebases and ontologies ..

> http://tech.groups.yahoo.com/group/projectAigo

Are things starting to break out all over ?? ;^)

= = =

> better avatars

Now there’s a clue! Better avatars are sorely needed! Personally, I would prefer to focus almost entirely on tooling my intelligence (domain specific conversational expert systems). I really find the lack of adequate visual and voice tools extremely distracting.

For instance, if we look at the SitePal model…. I would like better, more realistic avatars, perhaps full page, desktop, and mobile. (Don’t forget the Skype model could bypass web, desktop, and mobile altogether! ;^)) I want complete voice-interactivity, TTS + STT. I also require a cheaper monthly cost than SitePal. ;^) I think it should not be forgotten that a really good avatar system would be at least somewhat customizable, in terms features, hairstlyes, clothes, etc.

IMHO, any better avatar/voice technology should be DIVORCED from intelligence, and have a completely pluggable backend for ANY current “AI engine” (aka chatbot).

= = =

I’ve received some more detail about FIONA from Patricia Lopez of SparkingTogether. (It’s still not clear to me whether it’s called FIONA or SparkingTogether….) Apparently, FIONA will be something like an appstore, or API store, for cloud robotics, along the lines of MyRobots, StrongSteam, and Mashape. Supposedly the “sparks” being the individual modular contributions. What is not yet clear is whether it will be a closed or open ecosystem….

Just a reminder, this subject will be the topic of my presentation this month in Philadelphia at the Chatbots 3.2 Conference – Fifth Colloquium on Conversational Systems, “Open Chatbot Standards for a Modular Chatbot Framework”. Basically, I’ll be talking about the massive “Lego-ization” of cloud robotics, and a DIY Siri or Watson for everyman…. ;^)

=> http://chatbots32.eventbrite.com

= = =

http://sparkingtogether.blogspot.com

>> Fiona stands for Framework for Interactive-services Over Natural-conversational Agents. It is a collaborative platform to deliver interactive avatars that could be used in many devices, like kiosk, mobile phones or browsers. But that is only the tip of the iceberg. <<

Development › Designing and coding: Psychodynamics and chat bot

> http://en.wikipedia.org/wiki/Psychodynamics

I’m a psychologist by education, and am working up an extensive blog post on “Computational Dreaming” from a Jungian perspective. I’ll post something more to this thread later.

= = =

> http://www.meta-guide.com/home/robopsychology

I’ve begun putting together a new webpage all about “Robopsychology” (above link) as a result of this thread, enjoy!

General › AI thoughts: Conversational Expert Systems

Regarding my concepts of “Open Chatbot Standards” for a “Modular Chatbot Framework” ..

I’ve been seized by the idea that a dialog system (chatbot) need not incorporate an expert system, so long as it can call out to consult an expert system, for instance via API.

For example, if we call Apple Siri a dialog system and IBM Watson an expert system, then the availability of a Siri SDK and a Watson API would allow for integration.

At this point, I believe there is not sufficiently open and robust “AI middleware” available, much less cloud-based, to facilitate “rapid application development”. Not to mention the insufficient “interoperability” among currently available components.

Mark your calendars; as, I’m planning to expand on these concepts March 31 in Philadelphia at Chatbots 3.2 http://chatbots32.eventbrite.com ..

= = =

I haven’t come across PLOW (Procedure Learning on the Web) before.

I found some interesting videos about PLOW, including “PLOW iphone”, here:

http://www.youtube.com/user/syoutp98/videos

I’ve also put together a webpage analyzing the Google Scholar references to PLOW here:

http://www.meta-guide.com/home/bibliography/google-scholar/plow

PLOW seems to be classed together with “Web Macro” systems.

Development › My Chatbot Project: MALDIX

> 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

= = =

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.

News & Events › In the news: Will an AI become self aware?

> http://www.youtube.com/watch?v=TphFUYRAx_c

Check out this historic video, “QBO Robot in front of a mirror”….

General › AI thoughts: Software as a Service (SaaS) & Chatbots

> http://en.wikipedia.org/wiki/Software_as_a_service

What are the primary consumer oriented SaaS chatbots?

Pandorabots

Verbotsonline

MyCyberTwin

Chatbot4u

Why is there no SaaS available for ChatScript?

Why is there no SaaS chabot available with an API into (or out of) the knowledgebase?

Do you agree that in order to move conversational AI to the next level (in terms of stimulating the industry) that more and better SaaS chatbots are needed?

= = =

Maybe add PersonalityForge.com the list of SaaS chatbots.

A SaaS chatbot is basically a dialog system with a stock personality. A SaaS chatbot may or may not include an avatar frontend. That avatar may or may not include text-to-speech output. And ideally, it would also include speech-to-text input, such as with many mobile apps.

I really don’t think it should be necessary for everyone to reinvent the wheel from scratch every time. There are enough dialog systems, and enough stock personalities already. Why agonize over an animated avatar interface, with lipsync and TTS/STT? Shouldn’t these be simply MODULAR, mix and match components?

Beyond this, what I am desperately missing is the interactive API into the knowledgebase. The SaaS chatbot should become a kind of (cloud-based) “middleware” in order to facilitate the integration and infinite customization of knowledge via all the APIs available on the Web.

= = =

> http://www.google.com/search?q=site:mycybertwin.com+api

Hi Shaun, I wasn’t aware of that, thanks.

Now, is the company name CyberTwin or MyCyberTwin?? ;^)

You have both HTTP API & Javascript API??

Is there one place I can find more details about the API?

The “CyberTwin Comparison Table” states the API is only available in the “Enterprise” version at $15,000 per month, with initial build at $150,000 to $300,000….

At this point we move away from “consumer oriented SaaS chatbots” into B2C (CRM) and B2B (such as Artificial Solutions “MIA”).

General › New here? And general stuff: Verbot ?

The title of this tread is “Verbot ?” ..

I use http://verbotsonline.com and like it. In fact, my VagaBot is the most “popular” verbot online. ;^)

The animated talking avatar costs in one year what SitePal’s Pandorabots avatar costs in one month.

It is actually a little simpler to use than Pandorabots, though does have certain limitations along the lines of the differences between AIML and ChatScript.

You can find my VagaBot at http://meta-guide.com as well as http://Twitter.com/VagaBot .

General › AI thoughts: “Thotbot” and other ramblings….

> Open Chatbot Standards for an Open Chatbot Framework > http://www.meta-guide.com/home/open-chatbot-standards

Just today I’ve been motivated to begin collecting my recent thoughts on “Open Chatbot Standards for an Open Chatbot Framework” (above link).

I like the idea of a “language independent” framework; however, to me that does not necessarily mean “natural language”. For example, if various chatbot language interpreters offered APIs, then in theory we could run natural language through them without having to bother with the minutia of actually programming in each various chatbot language.

Further, if everyone offered an API, then APIs could be layered and mashed-up into a customized infinity of variations. However, in order to optimize mashing-up in this way an open (cloud) framework would be required.

On the subject of chatbots without natural language, so-called “thotbots”, it seems that would involve symbolic computation along the lines of Wolfram|Alpha’s Mathematica (or MATLAB). But, I could see APIs for this being mashed-up into an open chatbot framework.

Lastly, I’ve recently answered the following related question on Quora:

> Which language is best suited for communication with computer systems and artificial intelligence? > http://www.quora.com/Which-language-is-best-suited-for-communication-with-computer-systems-and-artificial-intelligence

Development › New to Chatbot programming: Building from the ground up?

I am not convinced that building a conversational agent from “scratch” is a good thing.

If you have settled on Python, then you should make a thorough inventory of the available resources, if for no other reason than to see how others approached it. The advantage of Python would be to use a cloud-hosted option such as Google App Engine, except the drawback is that uses flat files. I do not like your idea of changing horses in mid-stream.

However, it is also worth considering AI languages and available interpreters.

I believe, the best way is to think MODULAR, look for *frameworks*, and pluggable components. Actually, IBM Watson was made in this way. I believe, Apple Siri was also made like this.

= = =

> http://meta-guide.com/python-resources

James, I’ve made a webpage listing “Python Resources” (above), which includes many Python based chatbots of various kinds, among other potentially useful resources.

Should you find it helpful, you may buy me beer via the PayPal Donate button on my blog at http://mendicott.com . ;^)

Development › My Chatbot Project: ALF

Is everything command line, or do you have an avatar, any TTS or STT ???

Any way you could manage a narrated screencast upload to YouTube?

General › New here? And general stuff: Chatbot Charity

> http://www.indiegogo.com/Iphone-Chatbot

Steve!! Are you on Twitter?? Everyone really needs to be posting stuff like this to Twitter! (Hello, promotion ?!?) I’m happy to do it, of course as time allows, but I prefer to reference people (on Twitter). There is a Steve Worswick in Preston on Twitter, but you’re in Goole?

For people adverse to Twittering for whatever reason, its too easy to automate with feeds using services like http://twitterfeed.com and http://dlvr.it (in other words, just run your blog or whatever feed into your Twitter).

= = =

> http://www.facebook.com/people/Mitsuku-Bot/1604358768

Good news indeed, Steve!

Just a few quibbles about Facebook. “Mitsuku Bot” seems to be listed under “people”, rather than “pages” or “groups”. Also, I do not readily see the link to “Mitsuku Chatbot” http://mitsuku.com there under “info”. (Further, your Facebook does not seem to be actually linked from that website?) FWIW, its possible to run a feed from Facebook into Twitter, but I believe that functionality is only native for “pages”. Definitely, when you launch an app, you should consider widening your net. For instance, its also possible to run your Twitter feed into your LinkedIn, not to mention Google Buzz (and Google+).

General › New here? And general stuff: a-i.com

Note date: 2001

http://www.thestreet.com/story/10001139/startup-artificial-intelligence-closed-down.html

>> Startup Artificial Intelligence closed down

TheMarker.com Staff 09/17/01 – 10:16 AM EDT

Israeli startup Artificial Intelligence (AI) has been shut down, TheMarker.com has learned. Last Thursday the company gave notice to its 40 employers that it has ended its operation. No comment from AI could be obtained.

AI was founded in early 2001 by the former CEO of Magic Software Enterprises (Nasdaq:MGIC), Jack (Yaki) Dunietz, and was active in artificial intelligence. The company was busy developing an “electronic baby” based on academic research and psychological models.

The project aimed to develop a user interface that would enable full verbal communication between man and computer. Using artificial intelligence, it was supposed to give the computer the capabilities of a 15-month old baby.

The development was supposed to take ten years, at the end of which the electronic baby was expected to reach the mental level of a 12 year old child.

The company was apparently closed due to financing difficulties. Yaki Dunietz was the main source of funding of AI. Estimates are the company shutdown cost him several million dollars.

In the course of its activity the company was joined by Formula Systems (Nasdaq:FORTY) veterans, by the former managing director of the Hebrew language portal Walla Gadi Hadar, by the former Sivan Training & Systems Co Ilan Penn, and by former Magic executive Erez Baum. <<

= = =

http://www.a-i.com/show_tree.asp?id=36&level=3&root=33

June 05, 2010 : Ai and ILM release MyBot for iPhone and iPod touch

May 05, 2010 : Ai and ILM Announce MyBot for iPhone, iPad and iPod touch

February 28, 2010 : International Language Machines (ILM) Launches iHAL

October 27, 2009 : International Language Machines Announces iHAL

August 20, 2009 : Ai Releases MyBot for Live Messenger 2009

February 12, 2009 : New Release for MyBot

July 28, 2008 : MyBot for AIM is now available

March 16, 2008 : Ai Announces MyBot for Facebook

February 28, 2008 : Ai Introduces New MyBot Interface

October 29, 2007 : Ai Announces MyBot for the Web

July 19, 2007 : Ai Announces MyBot: A Conversational Virtual Companion

December 19, 2006 : Eyal Pfeifel re-joins Ai Research

March 01, 2006 : Experimental integration of Alan and VO Games interactive content technology

June 12, 2005 : New matching responses feature in HAL3000

January 05, 2005 : Ai releases HAL3000

January 02, 2005 : Ai Announces 2005 Research Objectives

November 01, 2004 : Ai Announces Sponsorship Program

July 12, 2004 : Ai releases HAL2004

April 28, 2004 : Ai launches new log viewing facility

January 01, 2004 : Ai announces 2004 research objectives

November 25, 2003 : Ai announces Private Virtual Personalities

June 10, 2003 : Ai releases HAL2003

November 01, 2002 : LMC2 Competition Canceled

September 02, 2002 : LMC2 Game Submission Update

May 27, 2002 : Ai Announces the Second Learning Machine Challenge

April 21, 2002 : HAL Goes Public

March 18, 2002 : LMC Steering Committee nominated

January 20, 2002 : Ai Announces Learning Machine Challenge Results

November 05, 2001 : 194 Submissions Received for Ai’s Learning Machine Challenge

September 16, 2001 : Ai to Reduce Level of Activities

August 05, 2001 : Ai Announces the Learning Machine Challenge: Win a Game Without Knowing Its Rules

April 01, 2001 : World’s Leading Artificial Intelligence Project Instates Israel’s Internet Pioneer as Vice President of Internet Operations

February 19, 2001 : Scientific breakthrough: Ai’s ‘baby’ computer program learns to converse like a 15 month-old human baby.

January 01, 2001 : Veteran Entrepreneur Takes Helm of World?s First Commercial Research Effort to Create True Artificial Intelligence

August 15, 2000 : Ai’s revolutionary approach to artificial intelligence presented at the American National Institute of Standards

July 15, 2000 : World’s First Commercial Effort to Create Artificial Intelligence Names One of Field’s Top Experts Chief Scientist

= = =

FYI

There are two LEARNING chatbots on Twitter http://twitter.com/twthal & http://twitter.com/beinspace that can apparently access WordNet and which are based on the a-i.com “Alan” engine (http://alan.<a href=“http://www.chatbots.org/company/mybot/”>a-i.com/</a>). (Just ask the bots!) I believe these bots have been developed by Eyal Pfeifel http://twitter.com/pfeifel (see December 19, 2006 release above). Its worth noting that Yaki Dunietz http://twitter.com/YakiDunietz & Erez Baum http://twitter.com/erezbaum can also be found on Twitter.

= = =

Erwin, you can try messaging Dunietz through Facebook

http://www.facebook.com/yakidunietz

= = =

FYI

Ai Research (a-i.com) has another company, International Language Machines http://language-machines.com, that makes iPhone apps (see also, releases above):

MyBot Creator for iPhone http://itunes.apple.com/app/mybot-creator/id375357166 “Teach your bot facts … through a normal English conversation.”

iHal for iPhone http://itunes.apple.com/us/app/ihal/id358399358 “iHal is a conversational learning system, trained to acquire language from a human trainer.”

I believe Dror Kessler http://twitter.com/dror_kessler is behind International Language Machines. And, his other website at http://www.spellmaze.com seems to be unreachable at the moment. (“SpellMaze from International Language Machines Ltd is a platform that enables users to interact with a set of words in a fun, easy way.”)

General › AI thoughts: Intelligent behavior

I’ve got some questions about parser technology. Keep in mind that I don’t have a formal education in NLP. My degree is in Psychology. (And, my IT background is a result of my father being a computer science professor.) I have done my own parsing, converting books into XML for example.

What actually is the parser doing? The example of Andrew’s results showed the parser was breaking out sentences from a text, and perhaps identifying them in dialog.

Is a parser then not a tagger? Is the parser adding metadata?

What is the relationship of “standard” parsers to semantic web data such as triples?

A simple seach for “parser AND RDF” lead me to Raptor RDF Syntax Library http://librdf.org/raptor/ , which mentions “serializers” in addition to parsers. What in fact is a serializer? What does it do?

Basic video tutorial suggestions welcomed! ;^)

= = =

Thanks for your feedback! Let’s see if I understand correctly?

= = =

1) tagger (http://en.wikipedia.org/wiki/Part-of-speech_tagging)

2) chunker (http://en.wikipedia.org/wiki/Shallow_parsing)

3) parser (http://en.wikipedia.org/wiki/Parsing)

4) parse tree (http://en.wikipedia.org/wiki/Parse_tree)

Question: What is the difference between a Parser and a Parser generator?

= = =

1) statistical tagger (http://nlp.stanford.edu/links/statnlp.html#Taggers)

2) named entity recogniser (http://nlp.stanford.edu/links/statnlp.html#NER)

3) chunker (http://nlp.stanford.edu/links/statnlp.html#NPchunk)

Question: Are there only Noun Phrase chunkers?

4) parser (http://nlp.stanford.edu/links/statnlp.html#Parsers)

5) parse tree or parse graph (http://nlp.stanford.edu/links/statnlp.html#Treebanks)

Question: Would a “statistical tagger” be a “probabilistic parser”, if so then where do “Semantic Parsers” fit in??

= = =

LinGO English Resource Grammar (ERG) http://www.delph-in.net/erg/ [HPSG]

HPSG http://en.wikipedia.org/wiki/Head-driven_phrase_structure_grammar

Question: In this case, a grammar is a thing; so, what does that thing look like, and what does it actually do (in the simplest terms)? (I’m less interested in the theory here and more interested in the thing itself.)

General › AI thoughts: Neats vs Scruffies

Andrew, thanks for that pointer!

My basic position is that the Turing test is a red herring.

Successful AI will be domain specific, augmentative and enhancing.

In terms of imaginary AGI, agents may exceed human capacities in distinct verticals, but human beings will not be “copied” in this century.

Certainly, IBM Watson’s success can be attributed to the “everything but the kitchen sink” approach.

Development › Designing and coding: Looking for computational linguist in Brazil

http://twitter.com/lingnet

LingNet UFRJ @lingnet Rio de Janeiro/Brasil Grupo de pesquisa do Programa Interdisciplinar de Pós-Grad. em Linguística Aplicada da Faculdade de Letras da UFRJ. http://www.lingnet.pro.br

Johan, these folks (above) are very interested in chatbots!

Development › Designing and coding: Chatbots on Deviantart.com

I just did a search of this AI Zone forum for “deviantart” and came up empty. I would like some help understanding the chatbots on Deviantart.com better. There seem to be MANY.

Obviously, Deviantart.com is an online community for artists, and logically some of the nicest basic web interfaces to chatbots can be found there, IMHO. I have done some digging and came up with the following; however, I still don’t fully understand how they’re being made, or in particular what AI engine they’re using??

http://twitter.com/mendicott/status/23140416948 >> http://botdom.com .. wiki for the #Botdom channel on @deviantART .. chatroom all about chatroom bots.. see also http://botlab.deviantart.com <<

https://twitter.com/mendicott/statuses/15847141801 >> Quite a few working chatbots at @deviantART with nice Flash interfaces => http://tinyurl.com/2dnmozu .. <<

General › New here? And general stuff: Why Are We Here?

> http://www.chatbots.org/expert/marcus_endicott/37/

I agree with Andrew’s suggestion that “Why Are We Here?” would be better than the “Community Contribution” on Chatbots.org profiles. (Somehow “Community Contribution” is very Dutch.)

I might add, I’m here to LEARN !

Development › New to Chatbot programming: Cleverbot

> http://twitter.com/mendicott/status/15331253101

“Over a million people visit http://cleverbot.com every day .. using http://4d.com (4D v11 SQL) .. according to co-developer @balinderwalia”

> http://infradrive.com/robomatic.php

“Microsoft .NET Framework 2.0”

Development › Platforms: Speech Recognition based-on Android

Speech recognition in Linux – Wikipedia http://en.wikipedia.org/wiki/Speech_recognition_in_Linux

List of speech recognition software – Wikipedia http://en.wikipedia.org/wiki/List_of_speech_recognition_software

Category:Speech recognition software – Wikipedia http://en.wikipedia.org/wiki/Category:Speech_recognition_software

Development › My Chatbot Project: Your Pandorabot HTML page.

http://aubreycraig.vhost.pandorabots.com/pandora/talk?botid=e0c4baaf3e345a44 http://aubreycraig.vhost.pandorabots.com/pandora/talk?botid=e73c7c655e345a9d http://carl-wetandchillychips.vhost.pandorabots.com/pandora/talk?botid=986bc2b6ae352a5b http://codony.vhost.pandorabots.com/pandora/talk?botid=e71c0d43fe35093a http://demo.vhost.pandorabots.com/pandora/talk?botid=804d3fdf1e34d9ff http://demo.vhost.pandorabots.com/pandora/talk?botid=816feb807e346456 http://demo.vhost.pandorabots.com/pandora/talk?botid=81a6f5941e34e377 http://demo.vhost.pandorabots.com/pandora/talk?botid=829713883e34f7 http://demo.vhost.pandorabots.com/pandora/talk?botid=829713883e34f760 http://demo.vhost.pandorabots.com/pandora/talk?botid=8a13eaa1ce351f26 http://demo.vhost.pandorabots.com/pandora/talk?botid=9451877b1e34467d http://demo.vhost.pandorabots.com/pandora/talk?botid=966fb6097e3611b0 http://demo.vhost.pandorabots.com/pandora/talk?botid=97cfdd9a1e35339a http://demo.vhost.pandorabots.com/pandora/talk?botid=984500bc9e35ed50 http://demo.vhost.pandorabots.com/pandora/talk?botid=9a6101260e362dcf http://demo.vhost.pandorabots.com/pandora/talk?botid=9b45bf88ce365bf5 http://demo.vhost.pandorabots.com/pandora/talk?botid=9dca4517ae344344 http://demo.vhost.pandorabots.com/pandora/talk?botid=a100a6c74e36bdab http://demo.vhost.pandorabots.com/pandora/talk?botid=a6be69d6ce36c22d http://demo.vhost.pandorabots.com/pandora/talk?botid=a93dcf79ae353e49 http://demo.vhost.pandorabots.com/pandora/talk?botid=aaa9db775e3480ae http://demo.vhost.pandorabots.com/pandora/talk?botid=b0dafd24ee35a477 http://demo.vhost.pandorabots.com/pandora/talk?botid=b4db4c279e3420eb http://demo.vhost.pandorabots.com/pandora/talk?botid=b800da72be34d5d9 http://demo.vhost.pandorabots.com/pandora/talk?botid=b9f70565fe3609ab http://demo.vhost.pandorabots.com/pandora/talk?botid=bb9d8db85e36d4b9 http://demo.vhost.pandorabots.com/pandora/talk?botid=c1776ae8ce354d1f http://demo.vhost.pandorabots.com/pandora/talk?botid=cbc227e28e355123 http://demo.vhost.pandorabots.com/pandora/talk?botid=ccfc31a34e3471a0 http://demo.vhost.pandorabots.com/pandora/talk?botid=d179a7ed2e35eaed http://demo.vhost.pandorabots.com/pandora/talk?botid=df127db4fe347130 http://demo.vhost.pandorabots.com/pandora/talk?botid=e10677c3ee36f742 http://demo.vhost.pandorabots.com/pandora/talk?botid=e4fc10b06e3632ef http://demo.vhost.pandorabots.com/pandora/talk?botid=ea048ff50e35986f http://demo.vhost.pandorabots.com/pandora/talk?botid=ebb1d8c23e35f252 http://demo.vhost.pandorabots.com/pandora/talk?botid=ecf251cfbe36e6e4 http://demo.vhost.pandorabots.com/pandora/talk?botid=f387faeeee341242 http://demo.vhost.pandorabots.com/pandora/talk?botid=f4c34aa14e3629d0 http://demo.vhost.pandorabots.com/pandora/talk?botid=f7634aec7e3652ed http://demo.vhost.pandorabots.com/pandora/talk?botid=f895b37a6e36b6d8 http://demo.vhost.pandorabots.com/pandora/talk?botid=fb113c764e34597f http://demo.vhost.pandorabots.com/pandora/talk?botid=fec6611fce344998 http://demo.vhost.pandorabots.com/pandora/talk?botid=ff35a54eee367fc1 http://drwallace.vhost.pandorabots.com/pandora/talk?botid=dc7ac68f6e36f134 http://drwallace.vhost.pandorabots.com/pandora/talk?botid=e365655dbe351ac7 http://elizabeth.vhost.pandorabots.com/pandora/talk?botid=f7634aec7e3652ed http://juan.vhost.pandorabots.com/pandora/talk?botid=a649e4ed5e34e5b3 http://lauren.vhost.pandorabots.com/pandora/talk?botid=f6d4afd83e34564d http://pandorabots.vhost.pandorabots.com/pandora/talk?botid=b823f27cce34ef1e http://philippe.vhost.pandorabots.com/pandora/talk?botid=94d255a09e366de1 http://rclee.vhost.pandorabots.com/pandora/talk?botid=ce837783de36f034 http://rclee.vhost.pandorabots.com/pandora/talk?botid=d37ddb790e36f0c1 http://rclee.vhost.pandorabots.com/pandora/talk?botid=e4116c5f5e36f951 http://rj.vhost.pandorabots.com/pandora/talk?botid=c1776ae8ce354d1f

Development › My Chatbot Project: Developing an AI, to those interested help would be appreciated

>> Also included in the design are my attempts at generating algorithms for dreams as they play an important role in improving mental models and input-output chaining in combination with short/long term memory to help the formation of complex ideas/outputs. <<

This I want to hear more about, “generating algorithms for dreams” ..

If you’re on Twitter, give me a follow at http://twitter.com/mendicott ..

= = =

Jon, are you on YouTube? I would like to see some kind of screencast highlighting your work .. Do you have *anything* that functions yet? What is your frontend, anything you can put on the web?? Are you blogging about your R&D?

BTW, I studied biological psychology for many years, and you seem to be coming as close as any cyberneticist I’ve come across ..

= = =

So, I just did a Google Scholar search for “allintitle: (algorithm OR algorithms) (dream OR dreams)” .. which revealed only one potentially pertinent title, “Genetic Algorithms at the Edge of a Dream” (1997) by Cathy Escazut http://bit.ly/lJncdl .. I then did another Google Scholar search on that title, and came up with “Continuous Parameters in Dreamy Genetic Algorithms” (2002) http://bit.ly/imSyaN by Gaudet, Chambers & Simon .. If anyone is aware of further published research in the area, I would very much like to learn of it ..

News & Events › In the news: The Chatterbot Collection Reloaded.

Roger, what’s your Twitter handle ?!?

Development › Tools, www.chatbots.org › Forum Home › General › AI thoughts: OpenEphyra

Think frameworks and libraries .. multi-agent systems are built on frameworks using libraries ..

For example, distributed multi-agent systems might take advantage of SaaS, API, or Webhooks ..

A cloud based framework, for instance Google App Engine or Amazon AWS, might be used to integrate various and sundry APIs into a unified frontend ..

I believe that Apple Siri was made in this way ..

I would remind everyone reading to think about potential “Open Chatbot Standards” ..

I’m particularly interested in XMPP as an open communication protocol among intelligent agents ..

= = =

Have you seen this one yet? How to build your own “Watson Jr.” in your basement => http://tinyurl.com/623te8x ..

Development › ChatScript: ChatScript GUI “Proof of Concept” app

Dave, do you do simple narrated screencasts? Do you have a YouTube channel? I would love to see more about your work in short videos (rather than having to spend days getting it all working on my tired hardware). Can we even embed videos in this forum?

Development › Platforms: Wiki-Botia

Erel, I’ve found you on LinkedIn; but, I can’t find you or http://trosinteractive.com on Twitter, which seems a bit odd since you’re in the “social knowledge” and “social analytics” business. Anyway, you can find me on Twitter at http://twitter.com/mendicot .

Development › Platforms: Are there any stand-alone chatbot software available to purchase?

Probably the premier turnkey chatbot today is Guile3D Denise http://www.guile3d.com ; however, I don´t know if its a learning bot per se, and am skeptical it could be integrated in the way you suggest, without significant expense.

Zabaware Ultra Hal Assistant http://www.ultrahal.com is a learning bot, but not clear to me that it could be integrated in the way you suggest.

Icogno/Existor Cleverbot http://www.cleverbot.com is another learning bot, but here again any integration such as you´re suggesting would be highend.

Perhaps someone else here can come up with a better suggestion?

= = =

The thing about chatbots is that there are three levels:

1) Intelligence

2) Avatar/Embodiment

3) Speech, Out & In

Most often when people talk about chatbots they are referring simply to intelligence, text-in & text-out.

Most commonly on the Web, even avatar-based (or embodied) chatbots (which may be talking heads or full body, either 2D or 3D) are still text-based.

Speech-out is fairly straight forward at this point, text-to-speech; however, speech-in or speech-to-text while do-able is still problematic at this point, though changing quickly.

To my knowledge Guile3D Denise is the first (decent) fully integrated chatbot product available for consumers. At $820 for their Denise Business product the version comparison below claims it does offer integration with 3rd party applications.

http://guile3d.com/en/compare-the-versions-and-find-the-best-for-you/

= = =

Chatbot developers need to be thinking about modularity. I don´t think its too early for chatbot developers to even be thinking about potentially porting their intelligences to hardbots (physical robots).

There is not a lot of competition for (decent) modular avatars such as SitePal at this point, and none for turnkey voice-in yet. I really want an avatar that can accept any major intelligence plug-in on the backend.

I don´t see why there is no mobile app available yet where I can simply talk with *ANY* AIML chatbot for instance?

Modularity in intelligence means pluggable to any major avatar system (XMPP compatibilty).

Modularity in avatars means fully dress-up enabled, in other words optimized for customization.

Modularity in speech means applicable to major avatar systems, as well as optimized for customization (voices, accents etc).

= = =

> http://silvia4u.com

http://twitter.com/CogCode has been very hushhush (cryptic) about their development. I´ve been unable to get anything coherent out of them. That 5k figure is news to me. I would definity be interested in more details, and better still seeing some demos.

= = =

Hi Andres, I’m interested in learning more about your platform, preferably in English.. (Mais, eu falo Portugues..)

I’m looking at three cloud-based NLP platforms at the moment:

1) GATEcloud.net

2) Wmatrix3 cloud

3) GramLab.org

Development › Platforms: RiveScript

Think:

http://www.personalityforge.com/

http://www.pandorabots.com/

http://www.verbotsonline.com/

http://www.chatbot4u.com/

Every new AI language such as RiveScript or Chatscript needs more than a bare bones interpreter, but needs a platform for the masses (ideally with an API). For people to really get into it, even explore and exploit properly, they need hands-on, user-friendly, cloud-based tools.

General › New here? And general stuff: Virtual Humans Forum co-operation?

> http://twitter.com/aidreamsforum

Roger, that´s a ten four! ;^)

= = =

Erwin, a feed is a feed, all items link back to the source. The nice thing about Twitter is everyone can see everything and potentially interact (multi) latterally. Personally, I get almost no DMs of any significance. (Maybe get 8man on the DM responder? ;^)) Look at feeds as outreach, promotion if you will. Everyone should institute their own feeds anyway, not least because they are MACHINE READABLE. For me, its just a matter of convenience, I prefer to get everything in one place. Twitter is great though, because it allows everyone to create their own feeds, both outbound and inbound. As you know I’ve been leveraging this to feed my chatbot knowledgebases via webfeed. ;^)

General › New here? And general stuff: Virtual Humans Forum co-operation?

Just picked up this thread on my iPod Touch while traveling in Uruguay .. using my unofficial Virtual Humans Forum feedbot, a kind of Twitterbot, at http://twitter.com/virtualhumans .. (also have one for this forum at http://twitter.com/chatbotsforum ..) Both feed into my Twitterlist at http://twitter.com/mendicott/chatbotters ..

Development › New to Chatbot programming: Project River — Need Starting Advice

Your programming skills sound better than mine. However, it seems hard to get enthusiastic about doing something from scratch. For instance, guile3d Denise is a pretty all inclusive product, and you can still customize the intelligence to your heart’s content. In any case, I reckon modularity is the key to any conversational agent. My feeling is that for practical purposes the AIML Superbot is all most people will ever need for the vast majority of interaction, and is still highly customizable. All the botmasters with learning chatbots seem overly squeamish about letting the general public use them, due to dragging them down to the lowest common denominator (dumbing-down effect). Basically, if a chatbot can’t handle real-world situations, then what good is it. Latent semantic indexing and probabilistic inference are likely more suited to big data, IMHO. I think it is important to keep in mind that humanoid robotics is predicted to become the biggest industry the world has ever seen, the question is just when. What I think this means for chatbot developers is that there will eventually be a great demand for a diversity of intelligence and character, maybe even more than for specific platforms. I can foresee intelligence and character being translatable between platforms; so in that sense, “mindfiles” could prove to be a better investment of time and energy than platform specifics. Like children, learning chatbots might take a long time to mature, and even then their direction can’t be guaranteed. ;^)

= = =

http://rebecca-aiml.sourceforge.net – cross platform open source AIML development platform for C++

http://shark-project.sourceforge.net – a modular C++ library for the design and optimization of adaptive systems

Development › My Chatbot Project: Thesis

I suspect you could use various current “sentiment analysis” tools to gauge stress.. I strongly urge trying to develop voice-in capability along the lines of MIT WAMI http://wami.csail.mit.edu .. Further, you should design it from the bottom-up to be deployable to mobile devices..

Development › Platforms: What is best program to create virtual girl ChatBot?

You seem to be familiar with what is generally available. Kari 3 is what came to my mind first. I guess you know about the new Guile3D Studio Denise? I don’t know much about Daz Studio; can you compare it with CrazyTalk? I believe there are some layers here, though haven’t completed them all myself.

– Animated avatar customization

– Lip syncing

– {Baldi Sync?} http://www.cslu.ogi.edu/toolkit/docs/2.0/apps/baldisync

– AI Interpreter

The question seems to be, how to interface the AI Interpreter (of which there are many) with the lip-synced animated avatar? There is a tool available called Baldi Sync; but, I haven’t used it yet. I believe Robert Medeksza of Zabaware is working on some kind of customizable avatar interface for his Ultra Hal.

I would definitely like more clarity in this area too!

= = =

Okay, I’m getting a little more clarity about the mystery of how the AI interpreter interfaces with avatar lip-syncing ..

I’ve found an informative paper by Ali Arya and Steve DiPaola, entitled “Face As A Multimedia Object” http://ivizlab.sfu.ca/media/WIAMIS.pdf ..

They describe how in their http://dipaola.org/lab/research/iface project that what they call the “Stream Layer” ( http://dipaola.org/lab/research/iface/iface2.jpg ) leverages the Microsoft DirectShow multimedia architecture ( http://en.wikipedia.org/wiki/DirectShow => http://upload.wikimedia.org/wikipedia/en/c/ce/Dsmp3graph.gif ) to split and decode the TTS input ..

Though, I still suggest going with CrazyTalk => http://forum.reallusion.com/Topic72574-251-1.aspx ..

Development › Designing and coding: Chatbot Final Year Project

http://www.mendicott.com/2009/03/feedbots-feeding-chatbots.html

>> Lately I have also been looking beyond the so-called stimulus-response systems to the new generation semantic systems, such as Stephen Reed’s texai.org, Sherman Monroe’s monrai.com and Ben Goertzel’s novamente.net.

Most basically the semantic systems strive to convert natural language into SPARQL queries and SPARQL queries into knowledgebases. (Note, relational databases may be converted into RDF, and become accessible to SPARQL, with D2RQ.) <<

= = =

AFAIK .. you would need to use a databased ALICE version, such as the newly popular Program-O (PHP/MySQL) .. If you must stick with Java, I suggest looking into RebeccaAIML.. To process semantic tagging, RDF metadata, you will need to store it in a MySQL/SQL compatible relational database, and then accomplish conversions into AIML within the database.. (One way to do this is by using XSLT..) You should look at the previous work of Eric Freese, which you can find here => http://tinyurl.com/2wnrudf .. BTW, some of the best minds in these fields are working on this right now, and have not yet solved it in an effective way..

Development › Platforms: alternative to sitepal

> http://twitter.com/mendicot/status/209701630428454912

Alan, I just tweeted about “Leslie Linguo” (above), great work!

= = =

> http://embots.dfki.de/EMBR/

EMBR: A Realtime Animation Engine for Interactive Embodied Agents

More to this thread, I’ve just come across this new avatar system from the German Research Center for Artificial Intelligence (DFKI), which looks promising!

Development › Designing and coding: Install a chatbot in my website

There are two ways you could approach this. Either use an online “Pandorabot” (http://www.pandorabots.com) with a http://www.sitepal.com talking avatar, or host your own linux-compatible AIML interpreter. http://rebecca-aiml.sourceforge.net has come highly recommended, but libaiml is also available for linux. The drawback with the sitepal.com talking avatar is that it is not cheap to use.

Development › Platforms: alternative to sitepal

FYI, there seems to be a new avatar design company “Emotion AI” at http://emotionai.com ..

http://alteregos.com seems quite like SitePal, but don’t know if supports AI easily like SitePal..

Facade, the Stanford Facial Animation System is worth checking at http://www.dipaola.org/stanford/facade/ ..

There is also Expression Facial Animation System at http://expression.sourceforge.net ..

And Robert Medeksza’s new Zabaware 3D Character Engine http://charengine.sourceforge.net ..

CrazyTalk 6 Facial Expression ToolKit (now $69.95) and CrazyTalk 6 Pro Animation ToolBox (now $179.95) Facial Animation Creator are available at http://www.reallusion.com/crazytalk/ ..

= = =

General › New here? And general stuff: Semantic Compaction Systems

> http://www.meta-guide.com/home/about/videography/best-minspeak-videos

Dave’s sudden accident, and the obvious inadequacy of chatbots as real world assisitve technology has started me thinking. Semantic Compaction Systems, such as Minspeak, a form of assistive sequential pictographic speech synthesis have just popped up on my radar for the first time. It’s like a different kind of chatbot for real people, facing real challenges. Minspeak reminds me of the work CereProc.com did reconstructing film critic Roger Ebert’s voice following thyroid cancer http://goo.gl/zpGnG .

General › AI thoughts: Task oriented AI verses converstational

Supposedly, one can cobble together a “supercomputer” using Amazon’s cloud services.

I’m still in the middle of investigating cloud databases. Right now, I’m leaning toward semantic databases. However, the best (free) ones are still in beta, so haven’t had the chance to actually test them yet.

I’ve got this concept of being able to cobble together a “Watson Junior” in the cloud. This concept involves my “Open Chatbot Standards” or “Open Chatbot Framework”.

I’m now looking for AI “middleware” in the cloud. The closest things I’ve found are GateCloud and JadexCloud (which doesn’t exist yet). With cloud-based AI middleware one would theoretically be able to cobble together many different cloud APIs, and therefore distribute a multi-agent architecture throughout the cloud. Actually, I believe, Siri is made in this way.

Sooo, I need a simple dialog system (interpreter), with a basic stock personality, in the cloud, in other words SaaS, that allows for API access into (and out of) its knowledgebase, in order to access the semantic expert system.

I would call this configuration a “Conversational Expert System”.

Please let me know of any potential problems you might see with this!

You can check my progress at http://meta-guide.com .