SIGIR 2010: Day 3 Industry Track Afternoon Sessions

While the SIGIR 2010 Industry Track keynotes had the highest-profile speakers, the rest of the day assembled an impressive line-up:

  • The new frontiers of Web search: going beyond the 10 blue links
    Ricardo Baeza-Yates, Andrei Broder, Yoelle Maarek, and Prabhakar Raghavan, Yahoo! Labs
  • Cross-Language Information Retrieval in the Legal Domain
    Samir Abdou and Thomas Arni, Eurospider
  • Building and Configuring a Real-Time Indexing System
    Garret Swart, Ravi Palakodety, Mohammad Faisal, Wesley Lin, Oracle
  • Lessons and Challenges from Product Search
    Daniel E. Rose, (Amazon)
  • Being Social: Research in Context-aware and Personalized Information Access @ Telefonica
    Xavier Amatriain, Karen Church and Josep M. Pujol, Telefónica
  • Searching and Finding in a Long Tail Marketplace
    Neel Sundaresan, eBay
  • When No Clicks are Good News
    Carlos Castillo, Aris Gionis, Ronny Lempel, and Yoelle Maarek, Yahoo! Research

I missed the Eurospider and Oracle talks, but otherwise I spent the afternoon enjoying these sessions. The slides, along with all of the keynote slides, are available here.

Some highlights from the talks I attended:

  • Andrei Broder, a pioneer of Web IR and author of the highly cited “Taxonomy of Web Search“,  enumerated a half-dozen challenges for web search to move from its current state to one that not only accomplishes semantic analysis but also supports task completion. Naturally, the one that appeals to me is the need for search engines to move beyond query suggestion and truly engage the user in a dialog.
  • Dan Rose talked about the challenges of product search, and in particular the blessing and curse of implementing search applications for structured data (something that I’m very familiar with from my previous role at Endeca). He also warned of the dangers of over-interpreting behavioral data, e.g., a site change that increases revenue does not necessarily imply a better user experience (it could just be favoring higher-priced inventory), and may ultimately alienate customers.
  • Xavier Amatriain focused on social search, and talked about how, as we’ve turned to context to help mitigate information overload, we find ourselves confronted with the new problem of context overload. Specifically, he cited the research questioning the wisdom of the crowd, and proposed the wisdom of the (expert) few as a better alternative.
  • Neel Sundaresan offered an interesting tour of eBay Research Labs prototypes, including the BayEstimate that helps sellers improve listing titles by discovering the keywords are both representative of the item and used in buyers’ queries.
  • Finally, Carlos Castillo offered a nice approach to discover when search engine abandonment is “good abandonment“: identify a subset of “tenacious” users who almost never abandon searches and measure their abandonment–since it is almost certain to be the good kind.

All in all, I was very impressed with the quality of the Industry Track, and gratified to see how it had improved on the program I put together last year. Given the key role that industry plays in information retrieval, I think it is important that the top-tier IR conference promote the best that industry has to offer.

By Daniel Tunkelang

High-Class Consultant.