The uncovering of hidden structures by latent semantic analysis
From MaRDI portal
Publication:2384532
Abstract: Latent Semantic Analysis (LSA) is a well known method for information retrieval. It has also been applied as a model of cognitive processing and word-meaning acquisition. This dual importance of LSA derives from its capacity to modulate the meaning of words by contexts, dealing successfully with polysemy and synonymy. The underlying reasons that make the method work are not clear enough. We propose that the method works because it detects an underlying block structure (the blocks corresponding to topics) in the term by document matrix. In real cases this block structure is hidden because of perturbations. We propose that the correct explanation for LSA must be searched in the structure of singular vectors rather than in the profile of singular values. Using Perron-Frobenius theory we show that the presence of disjoint blocks of documents is marked by sign-homogeneous entries in the vectors corresponding to the documents of one block and zeros elsewhere. In the case of nearly disjoint blocks, perturbation theory shows that if the perturbations are small the zeros in the leading vectors are replaced by small numbers (pseudo-zeros). Since the singular values of each block might be very different in magnitude, their order does not mirror the order of blocks. When the norms of the blocks are similar, LSA works fine, but we propose that when the topics have different sizes, the usual procedure of selecting the first k singular triplets (k being the number of blocks) should be replaced by a method that selects the perturbed Perron vectors for each block.
Recommendations
- Latent semantic analysis and Fiedler retrieval
- Unsupervised learning by probabilistic latent semantic analysis
- Latent semantic indexing: A probabilistic analysis
- Taking a new look at the latent semantic analysis approach to information retrieval
- Latent semantic analysis of the languages of life
- scientific article; zbMATH DE number 1301978
Cites work
- A Survey of Eigenvector Methods for Web Information Retrieval
- An algorithm for information structuring and retrieval
- ENTROPIC ANALYSIS OF THE ROLE OF WORDS IN LITERARY TEXTS
- scientific article; zbMATH DE number 1460605 (Why is no real title available?)
- scientific article; zbMATH DE number 3200675 (Why is no real title available?)
- IJCAI '01: 17th international joint conference on artificial intelligence (2-volume \& CD set)
- Latent semantic indexing: A probabilistic analysis
- Learning the parts of objects by non-negative matrix factorization
- Matrices with Low-Rank-Plus-Shift Structure: Partial SVD and Latent Semantic Indexing
- Non-negative matrix factorization with sparseness constraints
- On the Early History of the Singular Value Decomposition
- Spectral analysis of data
- The Rotation of Eigenvectors by a Perturbation. III
- Using Linear Algebra for Intelligent Information Retrieval
Cited in
(6)- Metaphor-based meaning excavation
- Neural memories and search engines
- scientific article; zbMATH DE number 1977814 (Why is no real title available?)
- scientific article; zbMATH DE number 2044713 (Why is no real title available?)
- Network-based dimensionality reduction for textual datasets
- Uncovering the roots of customer dissatisfaction via Amazon reviews: a hybrid ensemble-deep learning approach for e-commerce quality management
This page was built for publication: The uncovering of hidden structures by latent semantic analysis
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2384532)
