Atom Feed
October 5, 2004
The flood of emails from both sides spinning each detail of the debate has gotten to be hilarious. Email is not the right medium for this. We can wait ten or fifteen minutes. Besides, your chattering makes you sound frightened and like you don’t trust us. Shhhh. Drink some cocoa. It’ll be fine.
[NOTE: I have to the plane and am posting this without rereading it for typos or thinkos. Sorry.]
Susan Damais is from Microsoft Research, a group of 700 people in 55 scientific areas in 5 labs, from Redmond to Beijing. Susan says that each group does some search research. And she tells us that her presentation isn’t under the 20-ton Microsoft NDA.
“What’s missing with search?” she asks? Now it consists of a query box and results list. You can do processing in between, but you can also do user modeling, domain modeling, and the context of information use. What are the user’s intent? What are the relationships among people and informaion in the world? And what is the user trying to accomplish? (“Despite what you informavores believe, most people don’t search for the sake of searching. They search to get answers.” — rough paraphrase.)
She and others have been working on “Stuff I’ve Seen” (SIS). Right now, each domain has its own way of searching — we search blogs differently than we search email. SIS wants to give “unified access to heterogeous, distributed content” (mail, files, rss, etc.). It has to be fast and flexible. And you should be able to search from whatever context you’re in, preferably with “implicit queries”: “Queries are generated in context and results are shown in context.” “We’ve learned that people, time and metadata are important.”
She talks about “memory landmarks.” Cognitive science has shown that we organize memory around landmarks, e.g., not “It happened on Oct. 5” but “It happened when Mt. St. Helen’s blew up.” They want to use this to facilitiate search. In one prototype, there’s a set of memory landmarks, both general (world and calendar info) and personal (appointments and photos) they show to the right of the results list to provide cues to help you home in on the information you’re looking for. “I think we can get computationally at some of hese things that make information memorable.”
With personalized, users don’t all get the same results, she says. How can you personalize search without requiring people to maintain a profile, she asks. They can compute similarity based on a variety of apramets, combvine the personalized and standard results, and redisplay. In the prototype, as she moves a slider toward the “personalized” side, the results change, so that a query on “bush” starts to show more results about Vannevar Bush. (The personalization is based on looking at the user’s email, etc., and doing some form of ) It is not changing the query; it is re-ordering the results. [It’s a cool demo, but anything with a slider just has to be cool.]
She talks about novelty analysis, using the “Difference Engine” they’ve built. E.g., how do east and west coast newspapers cover Mt. St. Helen’s, or how blogs cover the election vs, how the media do. They have a prototype called News Junkie that pesonalizes news using onfromation novelty: What’s interesting and different? Given a lead article, how different are the new news articles coming out?
Eric Brill heads the Text Mining, Search and Navigation Group of Microsoft Research. He talks about the “paradigm shift” from thinking that documents are the chief object of search to think that it’s about information. That is, there may be information in documents that isn’t really what the difference about. Or, instead of getting a list of documents in response to a query trying to decide if the invasion of Iraq was justified, suppose you were to get a page that displayed the relevant information.
They have a question-answering system called “AskMSR” that gets 70-75% accurate. So, if you ask “Who did Britney Spears marry in Las Vegas,” you get a list of answers with probabilities; click on the suggested answer and you get the documents from which it’s derived. It gets right “Where as Steve Ballmer born” but wrong “Who ran against Bush in 1988,” to which it answers “Bush,” with “Dukakis” as the third suggestion. But, as Eric says, if you have a grain of intelligence, you’ll actually figure out what the right answer is.
It works by mining a text base looking for strings that look like potential answers. But then they run into natural language issues. But information redundancy helps. E.g., the answer to the question “Who killed Lincon?” shows up tens of thousands of times on the Web, so they don’t have to disambiguate “Booth altered history with a single shot at Lincoln”; they can pick their answer. Or, “How many times did Bjorn Borg win Wimbledon?” You can find lots of strings on the Net like “Bjorn Borg blah blah blah wimbledon bla bla blah 5 blah blah,” that, in their redundancy, make the answer (5) more probable. [Cool way to harness the wisdom of the web, at a statistical level.]
If you have a source like Encarta that is reliable but not redundant (i.e., it only has one entry that answers the question “When did the Titanic sink”?), you can combine it with the words found (statistically) on the Web around the Titanic to do precise queries against Encarta.
Finally, he talks about noisy channel information finding. For example, in spelling correction the system tries to figure out what the original (intended) spelling was based on the misspellings introduced by a “noisy channel.” We’re moving from “doe sthe page contain the query terms” to “Does the page satisfy the information need.”
Lili Cheng heads the Social Computing Group. Her group created “the personal map,” an app that models your social relationships as exhibited in your inbox/outbox, clustering based on who you email together. Her widget also has a slider that moves people into groups based on their groups. [Also cool. I tell ya, that slider thing never fails.] Then they took all of Microsoft’s public email lists and did the same sort of charts, a sort of “Six Degrees of Bill Gates.”
She shows us Wallop: “Socializing and sharing media in the context of your social network.” It’s a slick social network app with a bit of an emphasis on photo sharing. So far, only 424 have been invited into Wallop and 219 have added content. Wallop pays attention to implicit as well as explicit data, inferring your social network. People want to control it, but not have to control it all the time.
Wallop aims to integrate with the rest of your desktop, especially email.
They;re currently looking at how you scale it while maintaining privacy, and how to enable the system to adapt to user behaviour patterns rather than vice versa.
At the Search Champs private conference I’m at, Microsoft has been giving out excellent swag: A copy of Money, Office and Flight Simulator, a logo-ed windbreaker, sun visor and golf shirt, and a thumb storage device….all packed in a logoed-backpack. I’m too mature and self-knowing for swag to affect me, but I’m beginning to think that Microsoft has been badly misunderstood and under-appreciated. Plus, today we get to go to the Microsoft Store where we can spend up to $120 on heavily discounted Microsoft products. Unfortunately, I’m leaving before the trip to the store, so I assume I’m allowed to download $120’s worth of copyright-challenged Microsoft products via BitTorrent at Suprnova.org or the P2P network of my choice. That’s right, isn’t it?
Microsoft took us out to a lovely dinner last night. I sat with three Microsofties and, as always, was impressed with how crazy smart they are across such a wide range of interests. We talked frankly about the day, but also about Aristotle and the birth of persistent taxonomies, whether math escapes science’s revolutionary paradigm, whether art anticipates science, and why I don’t know what the hell I’m talking about when I mouth off about Wolfram. I had a great time and learned a whole bunch.
Sorry, I’d like to be snarky, but I’m just telling you the truth.
Today we have continuous access to the Net during the sessions. Thank you.
ThisIsRumorControl.com (“a blog dedicated to the “ground truth” that the war on terrorism is worth fighting, and al-Qaeda worth defeating, but the current U.S. policies in pursuit of these goals are failing our country in its moment of need”) is asking pumping a lecture series by Bobby Muller, head of the Alliance for Security, which is part of the Vietnam Veterans for America Foundation. Got that? I don’t, but if you’re interested in hearing Muller — Nobel Peace Prize winner as a co-founder of International Campaign to Ban Landmines — talk about the draft and the right use of force, here’s the schedule.
In about two minutes of poking around, I found one article I’m tempted to respond to in disagreement and a software recommendation that looks promising, so I figured I’d pass the link on to you. It’s a sorta-monthly webzine about Ilke Akdeniz’s (“one miserable freelance web designer”) ideas and opinions on web design, published out of Istanbul.
Ah the sound of the human voice. Gotta love it.
I understand why Ken Mehlman, as the Bush/Cheney campaign manager, in his latest msg pounds on Kerry’s “global test” statement, as if working with allies is the same thing as giving them a veto. But I can’t figure out how he can talk about Kerry’s “repeated denigration of our troops” at the debate. I mean, we were there. We heard him. Kerry could not have been more straightforward in his honoring our soldiers.
Yeah, yeah, I understand the logic: If you think a war is mistaken, you must also think the soldiers are mistaken. It’s stupid logic, but I understand it. What I can’t understand is why the Republican campaign thinks that, given Kerry’s actual statements and his demeanor, which we saw with our own eyes, we’re going to fall for this one.
(The subject line of the message is: “Fight the Spin – Spread the Truth!” Beyond spin and all the way to chutzpah.)
Australia is going to put records of all doctoral dissertations online in a searchable database. Great news, although I suppose technically it means that the Web has just gotten a bit more boring.
The article is a tad ambiguous. I think the database will contain the metadata, including an abstract, and not the dissertations themselves.
Ev’s leaving Blogger and Google because he accidentally discovered that the the light he was blocking because of screen glare wasn’t itself coming from the Internet.
Blogger.com was where Joho started. So, thanks, Ev for your role and your work. I look forward to seeing your next contribution, but for goodness sake, there’s no hurry!
October 4, 2004
There are about 35 white folks here, half from the US and half from Europe, Australia, New Zealand, and one from S. Africa. We’re here to provide “feedback” to Microsoft’s search development efforts. We are also obviously here to help us feel good about the efforts.
Attendees include people I’ve already met in the real world:
Buzz Bruggeman
Liz Lawley
Chris Pirillo
Robert Scoble
Dave Winer
Overall, based on how people introduced theselves, here’s the breakdown:
3 Search manipulators
2 Search bloggers
2 Mobile experts
7 writers/journalists (almost all international)
Internet rebel
5 site developers
2 Librarians
Musician
Story-teller
One woman
Plus there are a handful for MSN Product managers, PR people, and some Microsoft Research folks,
The NDA
We have all signed an NDA. A guy gets up to explain why and what it covers.
What we may not talk about: Product specific details (including images, features, demos, etc.), release schedules or plans.
What we may talk about: Purpose of event, basic event details, “what we talked about over cocktails”
If we have any doubts about what can blog, we can “run it by” Sean, the marketing guy who’s put the event together. If we fail to comply with the NDA we will be kicked out of the program and there could be “legal ramifications.”
The content
Having gotten past the NDA awkwardness – Microsoft is entitled to offer to show us stuff they don’t want us to talk about – we are now given a couple of hours of presentations that turn interactive faster than perhaps Microsoft expected. It is a lively discussion, let’s say. Some cool features and widgets, but also evidence of Microsoft’s unthought benevolent paternalism.
And, without having to run this past Sean, I believe that’s all I may say at this time.
Oh, good lunch. Creamy Mac and cheese for the veggies.
Microsoft is not providing connectivity during the conference I’m at, so I’ll be off the air for awhile. Frankly, it feels like they’re trying to hijack my attention and I resent it.
Later: Microsoft listened. Sort of. They’ve brought in enough lines for most of us to connect. Unfortunately, they have left them turned off until lunch lest our attention wander where it will go. So, I have been unable to google terms I don’t understand, check out web sites people have mentioned, and chat with Liz (who’s sitting next to me). Sigh.
Joho the Blog uses WordPress blogging software.
Thank you, WordPress!
