Michael Bendersky

About me

I am a PhD candidate at the Center for Intelligent Information Retrieval, Department of Computer Science, University of Massachusetts Amherst.

My current research combines insights from information retrieval, natural language processing and statistical machine learning to improve the effectiveness of search with complex natural language queries. I am excited about this research, since it has the potential to revolutionize the way people search on the web, in the enterprise and on mobile devices, to name just a few possible applications.

CV [pdf] @LinkedIn @Twitter @Google Scholar

Recent Publications & News

• M. Bendersky, D. Metzler and W. Bruce Croft: "Effective Query Formulation with Multiple Information Sources" In Proceedings of WSDM 2012 [pdf] [Best Paper Runner-up: Search Category]
• Following the 2nd Workshop on Query Representation & Understanding, Microsoft Research released a new QRU dataset [pdf]
• M. Bendersky, D. Metzler and W. Bruce Croft: "Parameterized Concept Weighting in Verbose Queries" In Proceedings of SIGIR 2011 [pdf] [Honorable Mention Award]
• A complete list of publications

Invited Talks

• Parameterzied Concept Weighting for Information Retrieval (RALI Lab, University of Montreal, September 2011)
• Learning Concept Importance Using a Weighted Dependence Model (Machine Learning & Friends Lunch, UMass Amherst, February 2010)
• Discovering Key Concepts in Verbose Queries (Technion, Israel Institute of Technology, January 2009)
• Long Queries and Short Documents (Microsoft Live Search, August 2008)