Fall Seminar Series  November 5, 2009
University of Minnesota
School of Statistics
College
of Liberal Arts

Learning to Rank for Web Search

Chris Burges
Microsoft Research
 

Thursday, November 5, 2009
3:30 PM, 115 Ford Hall
Minneapolis, East Bank Campus
Social at 3:00 PM, 300 Ford Hall

 

Abstract

I will give an overview of the machine learning techniques used to rank web search results in Bing, a commercial search engine. Learning to rank in this context presents some steep challenges: how do you rank tens of billions of documents in milliseconds?  How do you train models, given that your quality measure depends only on the ranked order of the results, thus requiring an objective function that is either flat or discontinuous everywhere?  How can you incorporate higher level semantic information, like clicks?  We certainly have boatloads of data - how might one go about visualizing it?