Title :
An evaluation of new and old similarity ranking algorithms
Author :
Lynch, Paul ; Luan, Xiaocheng ; Prettyman, Maureen ; Mericle, Lee ; Borkmann, Edward ; Schlaifer, Jonathan
Author_Institution :
Comput. Sci. Branch, Nat. Libr. of Med., Bethesda, MD, USA
Abstract :
The National Library of Medicine\´s (NLM) IRVIS project has been evaluating "similarity ranking" algorithms that reorder search results according to their similarity to a target result. Several variations of known ranking algorithms were tested, as well as one (we believe) new one which weights terms based on word length. When the algorithms were evaluated using the OHSUMED test collection, the new word length based algorithm was found to outperform the others.
Keywords :
document handling; information retrieval; IRVIS project; National Library of Medicine; OHSUMED test collection; similarity ranking algorithms; word length based algorithm; Biomedical communication; Biomedical measurements; Computer science; Data visualization; Frequency; Information retrieval; Information technology; Libraries; Organizing; Testing;
Conference_Titel :
Information Technology: Coding and Computing, 2004. Proceedings. ITCC 2004. International Conference on
Print_ISBN :
0-7695-2108-8
DOI :
10.1109/ITCC.2004.1286615
