In Text REtrieval Conference (TREC 2006), there are seven different information retrieval (IR) research areas, or tracks. Legal Track is a new track in TREC 2006. The goal of the legal track is to develop search technology that meets the needs of lawyers to engage in effective discovery in digital document collections. 100 GB OCR data, 7 million documents and 200 million unique terms in this legal corpus proposed us a great challenge. In this talk, we will present our conceptual relevance based query expansion model and discuss our experiences on Legal Track. The anatomy of Lucene, a gold standard text search engine library, will be introduced with the great stuff you always want to know about search engine.
Feng Charlie Zhao is a Ph.D. student in SCE at UMKC and a fellow in UMKC's Preparing Future Faculty Fellowship program. He received his B.S. from SIPE at Shanghai, China and M.S. from Larmar University at Larmar, U.S. His research interests are Computing with Relevance, Information Retrieval, Natural Language Processing, Semantic Web, P2P Network and Grid Computing.
For detailed information, visit the SCE Seminar webpage at http://www.csee.umkc.edu/csee-seminar.html