Berry, M. W., Dumais, S. T., and O'Brien, G. W.  Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Detecting Patterns in the LSI Term-Term Matrix - Kontostathis, Pottenger (2002) (1 citation) (Correct)
.... out the latent semantics in a collection of documents [5,7] LSI is based on well known mathematical technique called Singular Value Decomposition (SVD) The algebraic foundation for Latent Semantic Indexing (LSI) was first described in [5] and has been further discussed by Berry, et al. in [2][3]. These papers describe the SVD process and interpret the resulting matrices in a geometric context. The SVD, truncated to k dimensions, gives the best rank k approximation to the original matrix. In [19] Wiemer Hastings shows that the power of LSI comes primarily from the SVD algorithm. Other ....
Berry, M. W., Dumais, S. T., and O'Brien, G. W. (
A Mathematical View of Latent Semantic Indexing: - Kontostathis, Pottenger (2002) (Correct)
....of third order co occurrence. In section 4 we present trend data that explains term term matrix values in terms of the number of connectivity paths between terms. 3. RELATED WORK The algebraic foundation for LSI was first described in [5] and has been further discussed by Berry, et al. in [2][3]. These papers describe the SVD process and interpret the resulting matrices in a geometric context. The SVD, truncated to k dimensions, gives the best rank k approximation to the original matrix. The T and D matrices represent term and document vectors, respectively. In [16] Wiemer Hastings ....
Berry, M. W., Dumais, S. T., and O'Brien, G. W. (
Statistical Aspects of the WEBSOM System in Organizing Document .. - Kaski Lagus (1998) (7 citations) (Correct)
....of the documents can thus be enhanced by smoothing the histogram spatially on the map lattice. There exists, however, some evidence that at least in certain situations the smoothing has only a small effect (cf. Kaski, 1997a) 3. 4 Other Possible Encoding Methods Latent Semantic Indexing (LSI) (Berry et al. 1995; Deerwester et al. 1990) is one possible alternative document encoding method. One way of interpreting the LSI is that it represents the kth document by the vector a 0 k = X i a ki x 0 i ; 4) where a ki denotes the number of times the word i occurs in the kth document. The x 0 i is the ....
Berry, M. W., Dumais, S. T., and O'Brien, G. W. (1995).
How Well Can Passage Meaning be Derived without.. - Landauer, Laham.. (1997) (13 citations) (Correct)
....qualities, they pose a sufficient challenge to comprehension to provide an illuminating test of the sufficiency of the input. Latent Semantic Analysis (LSA) is a corpus based statistical method for inducing and representing aspects of the meaning of words and passages reflected in their usage (Berry, Dumais O Brien, 1995; Landauer and Dumais, 1996, 1997) 1 It is related to but different from some other corpus statistic methods (cf. Lund Burgess, 1995, in press; Sch#tze, 1992) In LSA a representative sample of text is converted to a matrix of word types by passages. Cell entries are the frequency of a given ....
Berry, M. W., Dumais, S. T. and O'Brien, G. W. (1995).
Assessing the Impact of Sparsification on LSI Performance - Kontostathis, Pottenger.. (2004) (Correct)
No context found.
Berry, M. W., Dumais, S. T., and O'Brien, G. W.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC