Dagstuhl Seminar on Content-Based Retrieval

Posted on April 21, 2009 by jeremy

As a researcher, it is occasionally quite interesting to reread thoughts and positions that I’ve taken in years and works past. Sometimes I can observe a marked shift from my previous thinking; avenues or approaches that I once considered fruitful I now no longer do. And sometimes I can observe hints and seeds of my current research; avenues of which I only had a vague inkling have blossomed into larger pursuits.

In April of 2006 I had the good fortune to attend a Dagstuhl Seminar on Content-Based Multimedia Information Retrieval (I am toward the upper left corner of the seminar group photo).  Ramesh Jain has a good writeup of Dagstuhl Seminars, what they are and how they work.  In the abstract of my Seminar presentation I wrote:

Continue reading →

Posted in Collaborative Information Seeking, Information Retrieval Foundations | 3 Comments

“Improving Findability” Falls Short of the Mark

Posted on April 16, 2009 by jeremy

Via Tim O’Reilly on Twitter, I came across this article by Vanessa Fox on how government can improve the findability of their web pages, and thereby allow citizens to become better informed and government to be more transparent.  Fox writes:

Continue reading →

Posted in Exploratory Search, Social Implications | 3 Comments

Universal, Google launch ‘Vevo’ Music Service

Posted on April 9, 2009 by jeremy

From Wired:

Vevo will launch later this year, a collaboration between Universal Music Group and Google the partners expect to be the leading music video service in the world from day one. Google confirmed to Wired.com Thursday that all of Universal Music Group’s video assets (music videos, interviews, concert footage and possibly Kyte-style backstage video) will live on Vevo

I scanned the news for information on what sort of search, organization and recommendation Google is planning on top of this music information, but could find no such announcement.

Unlike MySpace Music Vevo will not be a joint venture between Google and Universal, Google told Wired.com. The site will be wholly owned by Universal, the largest record label in the world, whose YouTube channel has more views than any other in the world (3.5 billion). Google will run all technology-related aspects of the service. “Universal owns the site, but Google/YouTube is providing the technology,” said a Google spokeswoman by e-mail.

Google is going to be responsible for all the technology, but it’s just not clear how much of that technology will be cloud and network infrastructure, versus the real good bits: search and recommendation.  That’s the stuff I’m reaaally curious about, the stuff that makes the whole endeavor interesting.

Posted in Music IR | Leave a comment

Retrievability

Posted on April 9, 2009 by jeremy

In my previous post I talked a little about the notion that big data alone cannot solve many of our problems.  I would like to give a more concrete example of this by discussing a paper published at CIKM 2008: “Retrievability: An Evaluation Measure for Higher Order Information Access Tasks” by Azzopardi and Vinay.  In large part, my desire to discuss this paper comes from a few of Peter Norvig’s comments in the aforementioned thread on big data: 

Continue reading →

Posted in Information Retrieval Foundations | 9 Comments

Large Data versus Limited Applicability

Posted on April 9, 2009 by jeremy

Large data can be extremely effective, but how widely applicable is it, really?

A week or two ago the blogosphere was abuzz with discussion about the Unreasonable Effectiveness of Data position paper by Googlers A. Halevy, P. Norvig, and F. Pereira.  I had my own commentary, but some great discussion came when Peter Norvig jumped in to the comments section of Daniel’s blog and clarified some of his points.  I have decided now to write a few followup posts on this topic, as it touches all sorts of information seeking behaviors and domains, from music recommendation to web search to enterprise search to exploratory search.

Continue reading →

Posted in Information Retrieval Foundations | 1 Comment

Music Explaura: Exploration and Discovery in Action

Posted on April 7, 2009 by jeremy

Music Information Retrieval continues to be an excellent place to play around with the intersection of search, recommendation, user-guided exploration, and explanatory (transparent) algorithms.

First, check out the announcement of Music Explaura from Stephen Green at Sun Research.  Stephen writes:

Continue reading →

Posted in Explanatory Search, Exploratory Search, Music IR | 1 Comment

Is the Ad-Sponsored Web Search Market a Conversation?

Posted on April 1, 2009 by jeremy

It has now officially been ten years since Christopher Locke, Doc Searls, and David Weinberger wrote the Cluetrain Manifesto, rekindling and reminding us of the centuries-old notion that markets are conversations between people, buyers and sellers. The following are a few of the Manifesto’s points that resonate with me:

Continue reading →

Posted in Explanatory Search, Social Implications | Leave a comment

Researcher on Fire

Posted on March 31, 2009 by jeremy

Over the past month and a half, computer science researcher and UQAM Professor Daniel Lemire has been on fire.  He’s written a series of blog posts on what it means to do research and be involved with a research community.  I’ve thoroughly enjoyed the whole series, and want to pass along pointers to his last 8 posts:

Continue reading →

Posted in General | 5 Comments

Collaborative Information Seeking (Ongoing Recap)

Posted on March 30, 2009 by jeremy

Now seems as good a time as any to post a quick recap of the series of collaborative information seeking posts that Gene and I have been writing over on Palblog.  We’re about halfway through the series.

I will post another recap once we finish the series.

Posted in Collaborative Information Seeking | 2 Comments

Google Music China launches

Posted on March 30, 2009 by jeremy

Well, the move comes 9 years after I suggested it to ’em, but Google finally launches a music service:

http://www.wired.com/techbiz/media/news/2009/03/reuters_us_google_china

Now, my only question is whether they have simultaneously been researching and implementing intelligent search algorithms to go with the free music downloads, or whether they have been too busy moving Microsoft Office into the online realm (aka Google Docs) and developing 3d avatar worlds (aka Google Lively) to work on their core mission: organizing the world’s (music) information.  The Wired article gives only scant details:

Users will be able to search by musical measurements such as the level of “beat” in a song and “instrumentality,” as well as by artist and song name.

I cannot believe that after 10 years of Music Information Retrieval research, this is all they have to offer.  If anyone has any details on the search offerings tied to this service, please let me know in the comments.

Posted in Music IR, Social Implications | Leave a comment