Text Retrieval Trials Focus on Searching Blogs and Legal Documents

The National Institute of Standards and Technology (NIST) is seeking participants for its next Text Retrieval Conference—TREC 2008. TREC is an annual evaluation campaign that provides the infrastructure for large-scale testing of search technology. Its purpose is to encourage more powerful, faster and easier-to-use technologies for retrieving information and to transfer the technologies to industry quickly. TREC 2008 has five tracks including one on blogs that includes tasks such as detecting blog posts that express positive or negative opinions on a subject. The legal track focuses on search technology to help the legal profession find digital information pertinent to a case in digital document collections; this year's focus is electronic discovery that includes word, email and voice "documents." For each track, NIST provides a test set of documents and search queries. Participants run their own text-retrieval systems on the data and return a list of the top-ranked retrieved documents to NIST. NIST pools the individual results and judges the retrieved documents to determine whether or not they match the criteria and evaluates the results. The TREC cycle ends with a workshop in November that is a forum for participants to share their experiences. Organizations wishing to participate must submit an application by June 12, 2008.

For more information, see http://trec.nist.gov/call08.html.