Speaker: Ariel Fuxman
Microsoft Research Silicon Valley
Title: Structured Entities in Web Search
Search engines today offer a rich user experience, no longer restricted to "ten blue links". For example, the query "Canon EOS Digital Camera" returns a photo of the digital camera, and a list of suitable merchants and prices. Similar results are offered in other domains such as food, entertainment, and travel. All these experiences are fueled by the availability of structured data about the entities of interest, and the ability to associate these entities to the user's queries.
In this talk, I will present my work on (1) associating Web queries with structured entities; and (2) building structured entity repositories. For the former, I will show how to leverage signals from the search engine query click logs to find the associations. For the latter, I will describe a system that exploits information from merchants to build a massive entity repository of significant practical importance: the product catalog of a Commerce search engine.
Ariel Fuxman is a researcher at Microsoft Research Silicon Valley, working at the Search Labs group headed by Rakesh Agrawal. His current research focuses on the application of database and data mining techniques to improve Web Search. He received his PhD. from the University of Toronto in 2006, and he was awarded the SIGMOD Jim Gray Best Dissertation Award for his work on query answering over inconsistent databases.