LatentSemanticIndex


Here are a couple of papers describing latent semantic indexing (LSI)

 

In class we'll go through:

lsiPaper_ut-cs-94-270.pdf

 

This paper appears to be the origin of the idea:

DeerwesterJASIS90.pdf

 

Here's a paper from Bellcore talking about how to improve LSI results:

improvingRetriefalBRMIC91.pdf

 

Here's a short survey with somewhat more recent citations:

informationRetrievalSurveyp11-raghavan.pdf

 

 

Here's package documentation for the R package "lsa" that does latent semantic analysis (same thing as lsi)

lsa.pdf