ETBLAST
From Wikipedia, the free encyclopedia
eTBLAST is a text similarity search engine currently offering access to the MEDLINE database, the National Institutes of Health (NIH) CRISP database, the Institute of Physics (IOP) database, and the NASA technical reports database. It is continuously expanding with additional text-based databases. The eTBLAST server compares a user's natural text query to target databases using a hybrid search algorithm consisting of a low-sensitivity weighted keyword-based first pass followed by a novel sentence-alignment based second pass. eTBLAST is a free web-based service of The Innovation Laboratory at the University of Texas Southwestern Medical School.
[edit] Interface
Because eTBLAST is a text-similarity engine rather than a simple keyword-based search tool, it is claimed that the user need not identify and manipulate query keywords and Boolean operators, as must be done for other search engines.
eTBLAST aims to help the user rapidly to find references, evaluate novelty, find experts and journals in a given topical area and track the popularity of the topic as defined by the user’s query.
A typical query of 100 words takes 1-2 minutes to return results after a comparison to MEDLINE that as of 1/1/2007 contains over 16 million records.
[edit] References
- James Lewis, Stephan Ossowski, Justin Hicks, Mounir Errami, and Harold R. Garner, Text Similarity: an alternative way to search MEDLINE, Bioinformatics, 15;22(18):2298-304, September, 2006.
- eTBLAST, was highlighted on the NetWatch column in Science, May 14, 2004, http://www.sciencemag.org/content/vol304/issue5673/netwatch.shtml
- Alexander Pertsemlidis and Harold R. Garner, Text Comparison Based on Dynamic Programming, IEEE Engineering in Biology and Medicine, Nov./Dec., 2004, Vol. 23, No. 6, pgs. 66-71.
