The Text Retrieval Conference (TREC) is a series of workshops designed to advance the state-of-the-art in information retrieval methodologies.
Each TREC consists of a collection of “tracks” that focus research attention on specific challenges.
This talk will give a brief summary of the history of TREC and then describe one or two tracks in more detail covering task definition, evaluation methodology, and lessons learned.
4:00 - 5:00 pm: Talk
5:00 - 5:30 Breakout Rooms
About Dr. Ellen Voorhees
Ellen Voorhees is a Computer Scientist at the National Institute of Standards and Technology (NIST). Her primary responsibility at NIST is to manage the Text REtrieval Conference (TREC) project [http://trec.nist.gov], a series of international workshops that defines methodology and builds infrastructure to enable large-scale evaluation of search technology for different tasks and across different media.
TREC has featured tracks in areas such as web search, question answering, search within free-text fields of medical records, e-discovery, and expert-finding. Voorhees' research focuses on developing and validating appropriate evaluation schemes to measure system effectiveness for these kinds of tasks.
She received a B.Sc. in computer science from the Pennsylvania State University, and M.Sc. and Ph.D. degrees in computer science from Cornell University. Prior to joining NIST she was a Senior Member of Technical Staff at Siemens Corporate Research in Princeton, NJ where her work on intelligent agents applied to information access resulted in three patents.
Voorhees is a Distinguished Scientist of the ACM where she is an active participant in its SIGIR (information retrieval) and SIGBio (bioinformatics, computational biology, and biomedical informatics) special interest groups. She was the general chair of the SIGIR 1997 conference and is on the editorial board of ACM TOIS (Transactions on Information Systems).
She is also a member of the Association for the Advancement of Artificial Intelligence (AAAI). She has published numerous articles on information retrieval techniques and evaluation methodologies and is a frequent reviewer for conferences, journals, and funding proposals in the ares of information retrieval and natural language processing.
Zoom Meeting - Details will be provided upon registration
(Membership: $30 Annually)