Matches in SemOpenAlex for { <https://semopenalex.org/work/W4294016653> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4294016653 abstract "The probabilistic topic model imposes a low-rank structure on the expectation of the corpus matrix. Therefore, singular value decomposition (SVD) is a natural tool of dimension reduction. We propose an SVD-based method for estimating a topic model. Our method constructs an estimate of the topic matrix from only a few leading singular vectors of the corpus matrix, and has a great advantage in memory use and computational cost for large-scale corpora. The core ideas behind our method include a pre-SVD normalization to tackle severe word frequency heterogeneity, a post-SVD normalization to create a low-dimensional word embedding that manifests a simplex geometry, and a post-SVD procedure to construct an estimate of the topic matrix directly from the embedded word cloud. We provide the explicit rate of convergence of our method. We show that our method attains the optimal rate in the case of long and moderately long documents, and it improves the rates of existing methods in the case of short documents. The key of our analysis is a sharp row-wise large-deviation bound for empirical singular vectors, which is technically demanding to derive and potentially useful for other problems. We apply our method to a corpus of Associated Press news articles and a corpus of abstracts of statistical papers." @default.
- W4294016653 created "2022-09-01" @default.
- W4294016653 creator A5012542050 @default.
- W4294016653 creator A5059289169 @default.
- W4294016653 date "2017-04-23" @default.
- W4294016653 modified "2023-10-17" @default.
- W4294016653 title "Using SVD for Topic Modeling" @default.
- W4294016653 doi "https://doi.org/10.48550/arxiv.1704.07016" @default.
- W4294016653 hasPublicationYear "2017" @default.
- W4294016653 type Work @default.
- W4294016653 citedByCount "0" @default.
- W4294016653 crossrefType "posted-content" @default.
- W4294016653 hasAuthorship W4294016653A5012542050 @default.
- W4294016653 hasAuthorship W4294016653A5059289169 @default.
- W4294016653 hasBestOaLocation W42940166531 @default.
- W4294016653 hasConcept C106487976 @default.
- W4294016653 hasConcept C109282560 @default.
- W4294016653 hasConcept C11413529 @default.
- W4294016653 hasConcept C114614502 @default.
- W4294016653 hasConcept C121332964 @default.
- W4294016653 hasConcept C136886441 @default.
- W4294016653 hasConcept C144024400 @default.
- W4294016653 hasConcept C158693339 @default.
- W4294016653 hasConcept C159985019 @default.
- W4294016653 hasConcept C164226766 @default.
- W4294016653 hasConcept C19165224 @default.
- W4294016653 hasConcept C192562407 @default.
- W4294016653 hasConcept C22789450 @default.
- W4294016653 hasConcept C33923547 @default.
- W4294016653 hasConcept C41008148 @default.
- W4294016653 hasConcept C42355184 @default.
- W4294016653 hasConcept C62520636 @default.
- W4294016653 hasConceptScore W4294016653C106487976 @default.
- W4294016653 hasConceptScore W4294016653C109282560 @default.
- W4294016653 hasConceptScore W4294016653C11413529 @default.
- W4294016653 hasConceptScore W4294016653C114614502 @default.
- W4294016653 hasConceptScore W4294016653C121332964 @default.
- W4294016653 hasConceptScore W4294016653C136886441 @default.
- W4294016653 hasConceptScore W4294016653C144024400 @default.
- W4294016653 hasConceptScore W4294016653C158693339 @default.
- W4294016653 hasConceptScore W4294016653C159985019 @default.
- W4294016653 hasConceptScore W4294016653C164226766 @default.
- W4294016653 hasConceptScore W4294016653C19165224 @default.
- W4294016653 hasConceptScore W4294016653C192562407 @default.
- W4294016653 hasConceptScore W4294016653C22789450 @default.
- W4294016653 hasConceptScore W4294016653C33923547 @default.
- W4294016653 hasConceptScore W4294016653C41008148 @default.
- W4294016653 hasConceptScore W4294016653C42355184 @default.
- W4294016653 hasConceptScore W4294016653C62520636 @default.
- W4294016653 hasLocation W42940166531 @default.
- W4294016653 hasOpenAccess W4294016653 @default.
- W4294016653 hasPrimaryLocation W42940166531 @default.
- W4294016653 hasRelatedWork W1515733880 @default.
- W4294016653 hasRelatedWork W1678711106 @default.
- W4294016653 hasRelatedWork W2007040503 @default.
- W4294016653 hasRelatedWork W2135569577 @default.
- W4294016653 hasRelatedWork W2890162296 @default.
- W4294016653 hasRelatedWork W2903666957 @default.
- W4294016653 hasRelatedWork W3048398186 @default.
- W4294016653 hasRelatedWork W3106260895 @default.
- W4294016653 hasRelatedWork W349217628 @default.
- W4294016653 hasRelatedWork W4289117577 @default.
- W4294016653 isParatext "false" @default.
- W4294016653 isRetracted "false" @default.
- W4294016653 workType "article" @default.