I attended one tutorial at AAAI. Usually a large conference like AAAI will begin with one or two days of tutorials, which are 4 hour classes that are meant to introduce a topic of current interest to an audience that might not know too much about it. I like to attend tutorials because they let me see how to present certain sorts of material (which I might need to do in one of my NLP classes) or they give me ideas about new research topics that I hadn't thought about too much.
So in summer of 2000 I went to a tutorial at NAACL given by Kevin Knight about Machine Translation. In the spring of 2001, I taught the graduate level NLP class and talked about the IBM statistical models of translation. Much of what I knew about those models was based on what I learned in the tutorial. Last summer I went to a tutorial at IJCAI about recommender systems. One of the presenters was Joe Konstan, who had been here earlier that year, so the tutorial was a nice follow on to that visit. This summer, I went to a tutorial about Bayesian Networks and Graphical Models, which are topics I used to spend lots and lots of time thinking about. So this was a nice refresher for me. The tutorial was presented by Kevin Murphy, now a post-doc at MIT, and soon to be a professor at the University of British Columbia. The tutorial presented a review of exact and approximate methods of interence in graphical models. I don't think I even want to try and get into the details of what that means. Just think of methods that let you represent and compute probabilities over a potentially complex event space in a reasonably efficient manner. If you have heard the term Bayesian Network before and are curious about it, I'd suggest checking out two different sources. First, there is a nice chapter on the topic in Russell and Norvig's AI Textbook. (http://www.cs.berkeley.edu/~russell/aima.html) Second, there are two very nice books by Judea Pearl that can be good starting points: 1) Causality: Models, Reasoning, and Inference (http://bayes.cs.ucla.edu/BOOK-2K/). 2) Probabilistic Reasoning in Intelligent Systems, Morgan-Kaufmann, 1988 During his tutorial, Kevin suggested a book by Finn Jensen called Bayesian Networks and Decision Graphs (Springer Verlag, 2001) as another nice starting point, so I plan to check that out as well. Kevin also wrote a tutorial a few years back about Bayesian Networks that still seems quite good to me... http://www.ai.mit.edu/~murphyk/Bayes/bnintro.html Finally, you can find all the slides and references from the tutorial at the url below. http://www.ai.mit.edu/~murphyk/AAAI04/ In any case, I attended this tutorial on Sunday afternoon, after having spent the morning at the Doctoral Consortium. Then I went out to dinner with the Doctoral Consortium group. It was a nice first day of the conference. :) Ted -- Ted Pedersen http://www.d.umn.edu/~tpederse ------------------------ Yahoo! Groups Sponsor --------------------~--> Yahoo! Domains - Claim yours for only $14.70 http://us.click.yahoo.com/Z1wmxD/DREIAA/yQLSAA/x3XolB/TM --------------------------------------------------------------------~-> Yahoo! Groups Links <*> To visit your group on the web, go to: http://groups.yahoo.com/group/nlpatumd/ <*> To unsubscribe from this group, send an email to: [EMAIL PROTECTED] <*> Your use of Yahoo! Groups is subject to: http://docs.yahoo.com/info/terms/
