[Top] [All Lists]

Re: [ontolog-forum] Ontology based conversational interfaces

To: Thomas Johnston <tmj44p@xxxxxxx>, "[ontolog-forum]" <ontolog-forum@xxxxxxxxxxxxxxxx>
From: Edward Barkmeyer <ebarkmeyer@xxxxxxxxxxxx>
Date: Thu, 16 Jul 2015 21:25:08 +0000
Message-id: <CO2PR11MB0005FE5559A12A0E49FE2937BC990@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx>



Yes, neurobiology was Jim Albus’ personal passion.  He thought robotic intelligence should mimic the human brain, so he kept abreast of every advance in understanding the latter.  One of his earliest electronics engineering projects (c. 1970) was a “cellular automaton” called CMAC, built for NASA, whose internal processing model was a neural network.  He was also very much interested in simulating human vision, with ever better cameras and image processing technology, then stereo imaging, and later radar and ladar imaging for automated vehicles in motion.  Jim was in fact a self-taught expert in human vision systems, and one of his leading subordinates was a Ph.D./M.D. physiologist (Dr. Ernest Kent).


As to the continuation of Jim’s direction of work, I suspect that some of his former co-researchers, students, and subordinates are carrying on research in what you call the “connectionist” paradigm, but I think most of the remaining group at NIST simply carries forward the general design ideas as guidelines.  This is partly because the thrust of the work in that Division has been redirected from on high, and partly because the NIST groups are now part of some joint government/industry/academic program in “cyberphysical systems”, which is primarily led by the principal academics involved.  The lead researcher at NIST in this area (I hope) is Dr. Elena Messina, who also worked with Jim for 20 years.  One of the academic leads in the joint activity is Prof. John Baras at U. Maryland (and whatever the associated NSF Research Center is called).  (I was not closely connected to that program.)




(erstwhile Systems Integration Division, NIST, which was spun off from Jim’s Robotics Systems Division in 1984, when we were all building a small totally automated manufacturing facility according to Jim’s principles.)





From: Thomas Johnston [mailto:tmj44p@xxxxxxx]
Sent: Thursday, July 16, 2015 12:55 PM
To: Edward Barkmeyer; [ontolog-forum]
Subject: Re: [ontolog-forum] Ontology based conversational interfaces




Your description is very helpful. Of course, given recently expressed concerns about AI, the notion of a Value Judgement component in a robot would certainly add fuel to the fire started by Elon Musk and Stephen Hawking (and the Terminator movies).


But I was under the impression that Albus did a lot of careful work in neurobiology. So did that work lead him to design an architecture for thinking machines, thus leading to the robotics work you describe?


Is his theoretical (connectionist) work being continued as its own discrete paradigm, or does it continue more as a set of guiding ideas in robotics?





On Thursday, July 16, 2015 12:44 AM, Edward Barkmeyer <ebarkmeyer@xxxxxxxxxxxx> wrote:


I worked with the late Jim Albus at NBS/NIST off and on for many years (1980-2005).  Most of his papers, although not his several books, are available from the NIST publications website:

The RCS papers that I remember are:

The latter was the magnum opus from his staff, but most of the architectural ideas in it came from Jim.  The earliest RCS papers (on “real-time control architecture”) that are still online are from the mid-1980s.


  Albus’s “Intelligent Systems Division” made major advances in the area of robotics using his control system ideas, including the “value judgment” (VJ) element of semi-autonomous systems.  The systems were used in NASA projects, military projects, and manufacturing projects.


In practice, the term VJ actually covered three different ideas:

- assessing whether a situation was generally consistent with, or a significant departure from, expectations

- assessing whether a situation posed a threat to the equipment, the work, or the environment

- determining the best choice among options for the next action or choice of route, based on some evaluation scheme, after taking account of the above.

In general, value judgment was how the controller determined the next course of action, given direction from a supervisor as to the task(s) to be performed and its own knowledge of safety and environmental concerns and a number of “sensory systems” by which it could form an opinion of the state of the world around it.





Edward J. Barkmeyer

Thematix Partners

Phone: +1 240-672-5800





From: ontolog-forum-bounces@xxxxxxxxxxxxxxxx [mailto:ontolog-forum-bounces@xxxxxxxxxxxxxxxx] On Behalf Of Thomas Johnston
Sent: Wednesday, July 15, 2015 4:58 PM
To: [ontolog-forum]
Subject: Re: [ontolog-forum] Ontology based conversational interfaces


Rich's James Albus reference was to a 1991 paper. Here's a reference to a 2008 paper of his.






On Wednesday, July 15, 2015 2:55 PM, Rich Cooper <metasemantics@xxxxxxxxxxxxxxxxxxxxxx> wrote:


A conversational system with flexibility will require an intelligent control system.  The usual linear system x[k+1] := A*x[k]+B*i[k] can be fashioned into the usual control system, but that is less flexible than I would like the conversational system to be. 


Here is an adaptation of linear systems to intelligent systems by adding a value judgment (VJ) subsystem to it.  The whole progression from standard linear system to value based system is shown at:



The so called RCS-4 version, the recommended intelligent control system, is described on that link, as summarized in overview here:


Value state-variables define what goals are important and what objects or regions should be attended to, attacked, defended, assisted, or otherwise acted upon. Value judgments, or evaluation functions, are an essential part of any form of planning or learning. The application of value judgments to intelligent control systems has been addressed by George Pugh.[16] The structure and function of VJ modules are developed more completely developed in Albus (1991).[2][17]


The Pugh reference is to RCS-4 concepts, while there is another Albus reference which includes figure 1 as the architecture overview below:



That architecture diagram is from:


"Outline for a Theory of Intelligence", which is in free PDF below:


The value judgment (VJ) module appears to steer the logic behind the Planning and Execution side of the diagram, at the whims of the World Model Database, while the old standby Situation Assessment side figures out what can possibly be thought, while the VJ module appears to figure out which thoughts work best of those available, and the planning and execution model decides what to focus on, schedule and do. 


A paper titled "A Value Driven System for Autonomous Information Gathering" is here:



Here is a fast summary of that paper's content:


And finally, there needs to be a script of textual utterances, with patterns to be matched against variable bindings.  Each node in the DAG should also have a slot for some function capable of estimating the value of each utterance to each goal, and the duration and cost of each utterance to utter and process. 


That is where the DAG comes in, IMHO.  Every statement that is matched would have follow on questions to ask, together with a new set of expected patterns to be matched.  The highest value, lowest cost question designed to elicit an answer previously unknown and undeducable from the current world model would be one way to choose the next question.  


But variation helps make the utterances more interesting.  So each node in the conversation DAG should be a possible child of a branching node which has both possible utterances as children, perhaps many more nodes, each with a possible next conversation move. 


Reviews of the discourse representation systems (DRS), especially Kamp's should help interested readers (like myself) to wrap some meat around those bones, so here is a reference to Kamp's work I found in PDF form:



Does anyone have references to a text generation paper they especially like?



Rich Cooper,

Rich Cooper,


Chief Technology Officer,

MetaSemantics Corporation

MetaSemantics AT EnglishLogicKernel DOT com

( 9 4 9 ) 5 2 5-5 7 1 2


-----Original Message-----
From: ontolog-forum-bounces@xxxxxxxxxxxxxxxx [mailto:ontolog-forum-bounces@xxxxxxxxxxxxxxxx] On Behalf Of John F Sowa
Sent: Tuesday, July 14, 2015 8:35 PM
To: ontolog-forum@xxxxxxxxxxxxxxxx
Subject: Re: [ontolog-forum] Ontology based conversational interfaces


Rich and Tom,


1983 was one of the "boom times" in the boom-and-bust cycle of AI.

That's when AI researchers were getting LISP machines and high-end workstations.  There was a lot of optimism about getting truly intelligent systems.  The Cyc project was started in 1984 with a 10-year plan to solve all the problems.



> a free pdf about discourse and conversational analysis:

> ian-brown-george-yule.pdf



> I think it's definitely worth a read, although, being published in

> 1983, most of its value probably lies in documenting the history of

> discourse analysis...


That book does a good job of surveying the complex issues about the semantics of natural language and the many, many ways that language is related to context, speakers, presuppositions, etc.


And they also show the huge number of reasons why we still do not have computer systems today that can understand natural language.


For just one of the many reasons why formal systems for NLP have failed, look at page 80 of that book (if you're using the Adobe reader, it's p. 47):


> In this approach, each participant in a discourse has a presupposition

> pool and his pool is added to as the discourse proceeds.  Each

> participant also behaves as if there exists only one presupposition

> pool shared by all participants in the discourse.  Venneman emphasizes

> that this is true in 'a normal, honest discourse'.


The last line is a typical method for dismissing all the hard parts.


The authors of the book recognize and discuss the many complex issues involved in that assumption.  Unfortunately, what Venneman calls "a normal, honest discourse" rarely, if ever, exists -- I don't believe that the terms 'normal' or 'honest' are appropriate.


Unfortunately, the boom years of the 1980s were followed by a typical bust, when people realized that language understanding is much harder than anybody in realized.  I often quote Alan Perlis:

"A year spent working in artificial intelligence is enough to make one believe in God."


Those issues are the theme of a talk I presented last year on "Why has AI failed?  And how can it succeed?"









Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/  
Config Subscr: http://ontolog.cim3.net/mailman/listinfo/ontolog-forum/  
Unsubscribe: mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
Shared Files: http://ontolog.cim3.net/file/
Community Wiki: http://ontolog.cim3.net/wiki/ 
To join: http://ontolog.cim3.net/cgi-bin/wiki.pl?WikiHomePage#nid1J    (01)

<Prev in Thread] Current Thread [Next in Thread>