Thu, Jan 27, 2011 @ 03:30 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Donald Metzler, USC, Information Sciences Institute
Talk Title: Learning to Effectively and Efficiently Rank at Scale
Abstract: anking functions serve as the \"brains\" of modern search engines. Developing ranking functions that are both effective (i.e., produce highly relevant results) and efficient (i.e., produce a ranking in a short amount of time) is a challenging research problem, especially when dealing with large document collections, such as the Web. Machine learning has been shown to be useful for learning highly effective ranking functions, but such approaches typically do not consider efficiency costs which are critical in real applications. In this talk, I will provide an overview of the challenges of ranking at scale and describe my recent research into leveraging machine learning to yield effective and efficient ranking functions for information retrieval applications.
Biography: Donald Metzler is a Research Scientist in the Natural Language group at the University of Southern California\'s Information Sciences Institute. Prior to joining USC he was a Research Scientist in the Search and Computational Advertising group at Yahoo! Research. He obtained his Ph.D. from the University of Massachusetts in 2007. His research interests include information retrieval, Web search, computational advertising, and applications of machine learning to large-scale text problems. He is currently serving on the senior program committees of WWW and SIGIR. He has published over 35 research papers, has 16 patents pending, and is the co-author of Search Engines: Information Retrieval in Practice.
Host: Prof. Louis-Philipe Morency
Location: Seaver Science Library (SSL) - 150
Audiences: Everyone Is Invited
Contact: Kanak Agrawal