Log in

No account? Create an account

Previous Entry | Next Entry

KDD Group Wiki plans

We're in the midst of reorganizing the KDD content-management system using TikiWiki, MediaWiki, and Joomla.

So far, URLs have been of the type:

This is achieved using a CNAME pointing to standard canonical URL:

What Seth Galitzer has recommended, and what we're now going with, is a vhost (propagating immediately with no DNS change):

In general:


should point to:


should point to:


are the canonical names to be given out.



( 9 comments — Leave a comment )
Feb. 3rd, 2007 07:51 pm (UTC)
Aside - discourse and Bayes
Hi Bill

I just found myself revisiting old work ... visualizations of climate change. Back in my VRML days I was big on creating "dashboards" to communicate the trends. HeyHo, that went nowhere.

I keep coming back to decision making in information-rich situations, and thinking again that things Bayesian are some way applicable. Would you tell me, have you encountered anyone whose work might relate Bayesian theories to discourse / discussion / dialectic / decisioning?

IPCC's documentation process is deliciously refined!
Feb. 3rd, 2007 08:56 pm (UTC)
Re: Aside - discourse and Bayes - part 1 of 2
Hi, Ben!

I'm not dead yet --- I've been in the midst of a couple of papers (one of which was just accepted yesterday to the International Conference on Weblogs and Social Media) and a grant proposal on comptranslation and other Human Language Technologies (HLT) due Mon 05 Feb 2007. I will have a bit more time to reanimate this blog and to follow up on interesting discussions after that's done.

As for Bayesian theories in discourse and dialogue, I was just talking with one of the participants in the HLT proposal about that yesterday. The state of the field, as you may know, tends more towards case-based reasoning (CBR) and analogy, but there is a trend in AI towards graphical models as causal representation. Here are specific Bayesian models that may be relevant:

  • Charniak and Goldman. There's a paper in Artificial Intelligence on a Bayesian network-based system for plan recognition.

  • The above is a precursor to the work of Horvitz, Heckerman, Cadez and Kadie of MS Research on related subjects (some of their applications, such as Lumiere, was billed as a "decision network for the Microsoft Office Assistant", which at the time was much reviled due to the high annoyance factor of Clippy). There's a Communications of the ACM article about this c. March, 1995 and some tech reports on Heckerman's publications page.

  • Since then, Bayesian networks have been used in user interfaces ranging from facial context tracking (Ashutosh Garg, an Illinois Ph.D. student at the time, gave a demo of this at IJCAI-2001 amid Gates's keynote talk) to web clickstream mining (the one by the above four authors was an application either for MS Small Business Server or the commerce server edition of IIS) to user modeling (Horvitz gave a demo of a prototype Outlook 2007 or Commerce Server app at UAI-2002 in Edmonton, that tracks "most probable time that someone will return from AFK").

  • Google is presently leading the field in certain aspects of information extraction, e.g., gist summarization, fusion of data sources for query answering (QA), etc. Peter Norvig gave a talk at IJCAI-2005 in Edinburgh titled "What to do with all the world's data".

BTW, there are of course many, many more applications than those developed by Microsoft and Google; these are just the ones I know of that spring immediately to mind. I did not go to IJCAI-2007 in Hyderabad last month, though I did send martin_samuel, so you might get a better state-of-the-field update from him this spring. I'll check with him.

I've been reading Pinker's The Language Instinct, Melamed's Empirical Methods for Exploiting Parallel Texts (reviewed here by Ted Pedersen and here by Constantin Orasan), and Gee's An Introduction to Discourse Analysis. When I've had a chance to digest the ideas and synthesize them more, and discuss them with my colleagues who have much more formal linguistics and cognitive linguistics background than I do, I will be able to give you a more useful answer.

What do you mean by "decisioning"? There are of course decision theoretic models of shared beliefs/desires/intentions as well as shared goals and responsibilities. Some of these have a probabilistic foundation.

Feb. 4th, 2007 12:58 am (UTC)
Re: Aside - discourse and Bayes - part 1 of 2
Strange ... I did not get email notification of this, your 1 of 2. Received notice only of 2 or 2.
Feb. 3rd, 2007 08:57 pm (UTC)
Re: Aside - discourse and Bayes - part 2 of 2
Katia Sycara at CMU does work on dialogue-driven negotiation, and you might take a look at the work of her (even) more Bayesian colleagues, Moshe Tennenholtz and Sarit Kraus.

I have an interest in Bayesian generative approaches to interactive fiction (IF), but it's on the back burner for now because of the information extraction (IE) and machine translation (MT) focus of our current work. IIRC, Mark Kantrowitz did some interesting work on IF at CMU in the early 1990s when he first started working on his Ph.D.

Thanks for the IPCC link! I'll look at it in about 55 hours. :-)

Feb. 4th, 2007 12:33 am (UTC)
Re: Aside - discourse and Bayes - part 2 of 2
Hey Bill ... thanks for this.

Sorry, but I'm not sure a 1998 cite from the ACM portal can be made into a hot lead. I mean, it's legit and all ... but I've been filling
[Error: Irreparable invalid markup ('<lj-user ="gnodal">') in entry. Owner must fix manually. Raw contents below.]

Hey Bill ... thanks for this.

Sorry, but I'm not sure a 1998 cite from the ACM portal can be made into a hot lead. I mean, it's legit and all ... but I've been filling <lj-user ="gnodal"> and other journals with that sort of thing since 1995.

Interactive fiction ... that's sweet. There's a Bayes connection here? My "Participatory Deliberation" is more along the line of enabling decision-making using dialectical processing, discourse analysis ... "forensic detail" is what I use to keep myself on track.

What comes to mind is the 1000s of scientists trying to see a way through the upcoming catastrophe ... alas, there's nothing fictionaly or literary about it. A Herculean challenge ... not sure we're up to it.

Feb. 4th, 2007 12:50 am (UTC)
Re: Aside - discourse and Bayes - part 2 of 2
Dang ... for not the first time that Portal leaves me feeling like I'm running in circles.

Sarit Kraus at UMaryland? Seems she's one of the many who don't really have a web-presence.

Anyhow, this is one of those tantalising threads that may well be worth tracking down. "Negotiation" can be likened to "decisioning" pretty easily ... stake-holders reaching something like concensus, if you know what I mean.

Feb. 4th, 2007 12:42 am (UTC)
Sweet stuff!

The material in my selections is a bit dusty ... I cobbled it together from email to myself 2003/04 after my HD failed.

"Decisioning" ... one of the few instances where I indulge the fad of transforming perfectly good active verbs into noun form.

I'm in a Catch-22 situation, Bill: unlike someone who's in a credentialled and salaried position, sharing my design ideas only leaves me more empoverished than my decades of pro bono work have already done. Let me just say that we're dialectical by nature ... and discourse (rather than conventional flat-page discussion as in sequential forums) can be used to make salient information discoverable.
Feb. 4th, 2007 01:50 am (UTC)
By way of context
Hi Bill

It occurs to me that I perhaps haven't communicated why I've for so long thought things Bayesian were at all implicated in my stuff. (I'm so usually dismissed that I've become slothful?)

A typical instance where my appetite is whetted:
"The key factors that determine what arguments to send are the desirability of the proposal to the proponent and the degree of trust (which describes how reliable or truthful the agent is) that exists between the two agents. These factors are then combined using a series of heuristics based on the believed motivations of the recipient to determine what persuasive strength of argument should be chosen in the prevailing context. Since these heuristics involve significant degrees of uncertainty it was decided to exploit fuzzy reasoning techniques."
"Persuasive Negotiation for Autonomous Agents: A Rhetorical Approach"; Sarvapali D. Ramchurn, Nicholas R. Jennings, Carles Sierra
( 9 comments — Leave a comment )

Latest Month

December 2008

KSU Genetic and Evolutionary Computation (GEC) Lab



Science, Technology, Engineering, Math (STEM) Communities

Fresh Pages


Powered by LiveJournal.com
Designed by Naoto Kishi