NOVEMBER CONFERENCE TACKLES TEXT RETRIEVAL SYSTEMS.

Everyone knows that "looking for a needle in a haystack" is tough work. However, when the needles are single bits of information and the haystack is the enormous collection of data available via the Internet, one needs help to do the search.

That's where text retrieval systems-the tools used to track down and isolate those needles-come in. Developing more powerful, faster and easier-to-use text retrieval systems to meet the demands of the Information Age requires a coordinated research effort. Therefore, NIST and the Defense Department have held the Text Retrieval Conference (known as TREC) since 1992 to provide the infrastructure necessary for large-scale evaluation of text retrieval methodologies. The 10th TREC will be held on Nov. 13-16, 2001, at NIST headquarters in Gaithersburg, MD.

TREC is overseen by a program committee consisting of representatives from government, industry and academia. For each TREC, NIST provides a test set of documents and questions. Participants run their own retrieval systems on the data and return to NIST a list of the retrieved top-ranked documents. NIST pools the individual results, judges the retrieved documents for correctness, and evaluates the results. The TREC cycle ends with a workshop that is a forum for participants to share their experiences.

This year, TREC is expanding to include, for the first time, a video track, because a growing amount of information is being stored in that form. This is a step toward including a general multimedia track in future years. Other topics will include web search engine systems and cross-language systems.

Attendance is limited to researchers and groups who submit search results to the conference. For more information on TREC, go to http://trec.nist.gov or contact Ellen Voorhees, [phone]; ellen. [e-mail].