Open AccessOn updating problems in latent semantic indexing
Author(s) -
Horst D. Simon,
Hanwen Zha
Publication year - 1997
Language(s) - English
Resource type - Reports
DOI - 10.2172/650342
Subject(s) - search engine indexing , computer science , latent semantic analysis , information retrieval , dimension (graph theory) , representation (politics) , probabilistic latent semantic analysis , process (computing) , data mining , artificial intelligence , mathematics , politics , political science , pure mathematics , law , operating system
The authors develop new SVD-updating algorithms for three types of updating problems arising from Latent Semantic Indexing (LSI) for information retrieval to deal with rapidly changing text document collections. They also provide theoretical justification for using a reduced-dimension representation of the original document collection in the updating process. Numerical experiments using several standard text document collections show that the new algorithms give higher (interpolated) average precisions than the existing algorithms and the retrieval accuracy is comparable to that obtained using the complete document collection