Chatbots Meta Guide


Open Chatbot Standards for a Modular Chatbot Framework

Web application framework (Middleware) | Cloud middleware (PaaS) | Cloud computing | Application programming interface

Notes:

The overriding purpose of this initiative is no less than to make the construction of intelligent agents accessible to everyman, and thereby contribute to jumpstarting the AI economy.  This framework should not only be useful for chatbots, or conversational agents, but also for any kind of intelligent agent.  I foresee a time in the not so distant future when people will no longer surf the Web as we know it today; they will instead use a layer of natural language agents, which will use the Web as we know it for their backend.

Increasingly cloud processing is being accomplished with Web APIs.  Generally, some kind of middleware will be necessary for the integration of multiple APIs.  An new trend is the appearance of “API Stores“, such as MyRobots, Strong Steam, and Mashape.  There are also numerous “API Management” companies available now for assistance.

Wikipedia:

Framework (computer science) | Interoperability | Modular programming | Open standard | Rapid application development | System integration | Usability | Web standards

Quora: 

What precisely differentiates SaaS, API and Webhooks? | Are there cloud-based Grammar Checking APIs available? | What cloud-based, purpose-built Triplestores are available?


Chatbots 3.2 – Marcus Endicott – Open Chatbot Standards for a Modular Chatbot Framework pt1of2 (Apr 15, 2012)

Chatbots 3.2 – Marcus Endicott – Open Chatbot Standards for a Modular Chatbot Framework pt2of2 (Apr 15, 2012)


March 2012

Sparking Together

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….  ;^)

February 2012

Sparking Together

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).

= = =

February 2012

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!

* * *

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!  ;^)

* * *

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)..

= = =

December 2011

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 ..

= = =

December 2011

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 .

= = =

November 2011

Are there any standard communication protocols for chatbots to talk to each other?

Gary, I have written extensively about the need for “Open Chatbot Standards” [1], and have frequently mentioned on Quora [2] the potential key role of XMPP for machine to machine natural language communication.

[1] http://www.meta-guide.com/home/open-chatbot-standards

[2] http://www.quora.com/Marcus-L-Endicott

FYI, I have also recently aggregated links and videos about “Multi Bot Scenarios” [3], such as the viral “AI vs AI”.

[3] http://www.meta-guide.com/multi-bot-scenarios

BTW, my personal feeling about the Turing test is that it is a “red herring”.

= = =

September 2011

End-to-end NLP packages

Next question ..

What “end-to-end” NLP packages are available in the “cloud” ?

i.e. .. corpus (ePub) | {cloud} | natural language i/o

I’m dreaming of a (open) cloud-based framework for a plethora of pluggable APIs ..

= = =

September 2011

“Thotbot” and other ramblings….

Just today I’ve been motivated to begin collecting my recent thoughts on “Open Chatbot Standards for an Open Chatbot Framework” ..

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.

= = =

September 2011

What is the next big thing in Instant Messaging?

I feel strongly that there will be a boom in XMPP for machine-to-machine natural language communication (AI vs. AI).

Extensible Messaging and Presence Protocol http://en.wikipedia.org/wiki/XMPP

Further, if there were any decent IM-Voice bridge (app) available, then not only would everyman have safer hands-free instant messaging, but would also be able to speak with their own AI using speech i/o.

= = =

September 2011

Artificial Intelligence AppStore

Some more thoughts on “Standards for commercializing chatbots” …

More and more, I’m focussing on APIs and the cloud. I can’t stress my desire for more MODULARITY, all levels of plug and play modules from all players. I still have the vision of “Open Chatbot Standards” for an “Open Chatbot Framework”. So, has the time come for an Artificial Intelligence AppStore, such as Strongsteam (http://strongsteam.com/)?

For example, if there were a Cleverbot API and an IBM Watson API, I could see a layered “mashup” of the two being “white labeled” in the cloud. This would allow for highly customized agents, to be built by the masses.

That would require some kind of “Open Chatbot Framework” (in the cloud). Right now, I’m using Yahoo! Pipes for mashing up my agents and bots in the cloud.  However, I need something more semantic along the lines of DERI Pipes (http://pipes.deri.org/) to integrate a rules layer to actually make chatbots think, to take advantage of the broader semantic web movement.

As usual I would appreciate any feedback on this to get more grounded about feasibility, timeliness, or just brainstorm, etc.

= = =

August 2011

What traits should the ideal chatbot authoring language have?

Gary, as you probably know, there’s been a lot of talk on Robitron and the Chatbots.org AIZone about Bruce Wilcox’s ChatScript (versus AIML). There is also RiveScript by Noah Petherbridge, CML (Conversation Markup Language) by Chongguan Yang, and AIScript (PersonalityForge) by Benji Adams. The list goes on.

Current Loebner champion Wilcox has waxed eloquent about this in March 2011, “Beyond Façade: Pattern Matching for Natural Language Applications” ..

He revealed more details about his work in June 2011, “Suzette, the Most Human Computer” ..

As I’ve mentioned previously on Chatbots.org AIZone, its not so much the language as the interpreter that makes the most difference to the learning curve. (Though I do agree theoretically with the logic for the improvements of ChatScript over AIML.) Its in fact the (cloud) infrastructure of new services like Chatbot4u that make the most difference. It just feels like to me that the old days of hosting an interpreter on your own hardware are quickly passing away.

That said, I’m a great believer in MODULARITY, open plug and play frameworks. I believe, both Apple Siri and IBM Watson were made in this way. Currently, the biggest bottleneck is the voice-in/voice-out lipsync avatar. I am a big promoter of XMPP as the lingua franca for open, modular conversational agents. But, there is no good IM-Voice bridge available at this time (with or without avatar).

= = =

July 2011

Re: Question about Chatscript engine.

It sure would be nice if there were some kind of SaaS interface for Chatscript, like Pandorabots.  In fact, I would love to have a Chatscript engine API available online.  This is inline with my “Open Chatbot Standards” or “Open Chatbot Framework” concepts of modularity, maximum plug and play for everyman.

= = =

June 2011

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 ..

= = =

May 2011

Standards for commercializing chatbots

I´ve been mostly offline the past four months traveling in South America, and am still in Buenos Aires today. I´m thinking about standards for chatbot commercialization, and wanted to let this brainstorm fly for any potential feedback on this subject.

Currently, I´m seeing three levels of products:

1) Intelligence (chatbot engines)
2) Avatars systems
3) Interactive speech technologies (TTS + STT)

My belief continues to be that XMPP is the lingua franca for chatbots, allowing them to communicate with other networked systems, including avatar systems, and indeed one another.

I don´t know of many “modular” turnkey avatar systems yet. I suppose there is SitePal, and various SecondLife products could be considered similar. I understand Zabaware is working on something like this. I´m assuming some level of lipsync built into avatar systems, or not.

Of course, the speech technologies are in great flux right now, particularly regarding web service APIs. How they may shake out is anyone´s guess at this point, but I can imagaine XMPP also being involved at this level, potentially for interfacing modularized avatar systems.

Somehow this notion of a standard “modularity” in this area seems to open a lot of ground for the participation of an even wider array of industries in the overall effort.

(I won´t even get into the potential convenience of XMPP for interfacing “intelligences” with future hardbots, or physical robots, at this point.)

That´s it for now! ;^) All feedback, both positive and negative, much appreciated!


References:

See also:

100 Best Chatbot Videos | 100 Best Chatbots VideosApplication Programming Interfaces | Artificial Intelligence Middleware | API Stores | API Management | Best Chatbot4U Videos | Best SecondLife Chatbot VideosChatbot API (Application Programming Interface) | Marcus L Endicott: Chatbots.org AI ZoneMeta Guide System Architecture (Chatbot Chakras)