FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186201162> ?p ?o ?g. }

• W3186201162 endingPage "e608" @default.
• W3186201162 startingPage "e608" @default.
• W3186201162 abstract "Hierarchical topic modeling is a potentially powerful instrument for determining topical structures of text collections that additionally allows constructing a hierarchy representing the levels of topic abstractness. However, parameter optimization in hierarchical models, which includes finding an appropriate number of topics at each level of hierarchy, remains a challenging task. In this paper, we propose an approach based on Renyi entropy as a partial solution to the above problem. First, we introduce a Renyi entropy-based metric of quality for hierarchical models. Second, we propose a practical approach to obtaining the “correct” number of topics in hierarchical topic models and show how model hyperparameters should be tuned for that purpose. We test this approach on the datasets with the known number of topics, as determined by the human mark-up, three of these datasets being in the English language and one in Russian. In the numerical experiments, we consider three different hierarchical models: hierarchical latent Dirichlet allocation model (hLDA), hierarchical Pachinko allocation model (hPAM), and hierarchical additive regularization of topic models (hARTM). We demonstrate that the hLDA model possesses a significant level of instability and, moreover, the derived numbers of topics are far from the true numbers for the labeled datasets. For the hPAM model, the Renyi entropy approach allows determining only one level of the data structure. For hARTM model, the proposed approach allows us to estimate the number of topics for two levels of hierarchy." @default.
• W3186201162 created "2021-08-02" @default.
• W3186201162 creator A5003789282 @default.
• W3186201162 creator A5026589408 @default.
• W3186201162 creator A5053947754 @default.
• W3186201162 creator A5063666310 @default.
• W3186201162 date "2021-07-29" @default.
• W3186201162 modified "2023-09-27" @default.
• W3186201162 title "Analysis and tuning of hierarchical topic models based on Renyi entropy approach" @default.
• W3186201162 cites W1494021613 @default.
• W3186201162 cites W1516407653 @default.
• W3186201162 cites W1976645892 @default.
• W3186201162 cites W2001082470 @default.
• W3186201162 cites W2004745914 @default.
• W3186201162 cites W2005564522 @default.
• W3186201162 cites W2134731454 @default.
• W3186201162 cites W2150286230 @default.
• W3186201162 cites W2158266063 @default.
• W3186201162 cites W2162317738 @default.
• W3186201162 cites W2167191107 @default.
• W3186201162 cites W2341256577 @default.
• W3186201162 cites W2412366109 @default.
• W3186201162 cites W2517406995 @default.
• W3186201162 cites W2561206696 @default.
• W3186201162 cites W2742276251 @default.
• W3186201162 cites W2798798513 @default.
• W3186201162 cites W2954426168 @default.
• W3186201162 cites W2962803562 @default.
• W3186201162 cites W2962967218 @default.
• W3186201162 cites W3014013476 @default.
• W3186201162 cites W4308951891 @default.
• W3186201162 cites W747801556 @default.
• W3186201162 cites W5221400 @default.
• W3186201162 doi "https://doi.org/10.7717/peerj-cs.608" @default.
• W3186201162 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8330431" @default.
• W3186201162 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34401473" @default.
• W3186201162 hasPublicationYear "2021" @default.
• W3186201162 type Work @default.
• W3186201162 sameAs 3186201162 @default.
• W3186201162 citedByCount "4" @default.
• W3186201162 countsByYear W31862011622022 @default.
• W3186201162 countsByYear W31862011622023 @default.
• W3186201162 crossrefType "journal-article" @default.
• W3186201162 hasAuthorship W3186201162A5003789282 @default.
• W3186201162 hasAuthorship W3186201162A5026589408 @default.
• W3186201162 hasAuthorship W3186201162A5053947754 @default.
• W3186201162 hasAuthorship W3186201162A5063666310 @default.
• W3186201162 hasBestOaLocation W31862011621 @default.
• W3186201162 hasConcept C106301342 @default.
• W3186201162 hasConcept C119857082 @default.
• W3186201162 hasConcept C121332964 @default.
• W3186201162 hasConcept C124101348 @default.
• W3186201162 hasConcept C134306372 @default.
• W3186201162 hasConcept C141318989 @default.
• W3186201162 hasConcept C144986985 @default.
• W3186201162 hasConcept C154945302 @default.
• W3186201162 hasConcept C162324750 @default.
• W3186201162 hasConcept C169214877 @default.
• W3186201162 hasConcept C171686336 @default.
• W3186201162 hasConcept C182310444 @default.
• W3186201162 hasConcept C31170391 @default.
• W3186201162 hasConcept C33923547 @default.
• W3186201162 hasConcept C34447519 @default.
• W3186201162 hasConcept C41008148 @default.
• W3186201162 hasConcept C500882744 @default.
• W3186201162 hasConcept C62520636 @default.
• W3186201162 hasConcept C80444323 @default.
• W3186201162 hasConcept C8642999 @default.
• W3186201162 hasConcept C9679016 @default.
• W3186201162 hasConceptScore W3186201162C106301342 @default.
• W3186201162 hasConceptScore W3186201162C119857082 @default.
• W3186201162 hasConceptScore W3186201162C121332964 @default.
• W3186201162 hasConceptScore W3186201162C124101348 @default.
• W3186201162 hasConceptScore W3186201162C134306372 @default.
• W3186201162 hasConceptScore W3186201162C141318989 @default.
• W3186201162 hasConceptScore W3186201162C144986985 @default.
• W3186201162 hasConceptScore W3186201162C154945302 @default.
• W3186201162 hasConceptScore W3186201162C162324750 @default.
• W3186201162 hasConceptScore W3186201162C169214877 @default.
• W3186201162 hasConceptScore W3186201162C171686336 @default.
• W3186201162 hasConceptScore W3186201162C182310444 @default.
• W3186201162 hasConceptScore W3186201162C31170391 @default.
• W3186201162 hasConceptScore W3186201162C33923547 @default.
• W3186201162 hasConceptScore W3186201162C34447519 @default.
• W3186201162 hasConceptScore W3186201162C41008148 @default.
• W3186201162 hasConceptScore W3186201162C500882744 @default.
• W3186201162 hasConceptScore W3186201162C62520636 @default.
• W3186201162 hasConceptScore W3186201162C80444323 @default.
• W3186201162 hasConceptScore W3186201162C8642999 @default.
• W3186201162 hasConceptScore W3186201162C9679016 @default.
• W3186201162 hasLocation W31862011621 @default.
• W3186201162 hasLocation W31862011622 @default.
• W3186201162 hasLocation W31862011623 @default.
• W3186201162 hasLocation W31862011624 @default.
• W3186201162 hasOpenAccess W3186201162 @default.
• W3186201162 hasPrimaryLocation W31862011621 @default.
• W3186201162 hasRelatedWork W2084269532 @default.
• W3186201162 hasRelatedWork W2089421272 @default.

• next