Title :
Information retrieval with principal components
Author_Institution :
George Washington Univ., Washington, DC, USA
Abstract :
Latent semantic indexing is a linear data reduction technique used in informational retrieval applications. The method of principal components is a popular linear data reduction technique that has been used in many applications. In this paper how the principal components method is used in information retrieval is presented, and how the latent semantic indexing is related to the principal component method is shown. Two experiments of monolingual and multilingual searches are described to show the feasibility of the method of principal components in information retrieval.
Keywords :
data reduction; indexing; information retrieval; principal component analysis; information retrieval; latent semantic indexing; linear data reduction; monolingual searches; multilingual searches; principal components; Data mining; Feature extraction; Indexing; Information retrieval; Information technology; Matrix decomposition; Search methods; Singular value decomposition; Vectors;
Conference_Titel :
Information Technology: Coding and Computing, 2004. Proceedings. ITCC 2004. International Conference on
Print_ISBN :
0-7695-2108-8
DOI :
10.1109/ITCC.2004.1286463