Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136237185> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3136237185 endingPage "5653" @default.
- W3136237185 startingPage "5639" @default.
- W3136237185 abstract "Deep probabilistic aspect models are widely utilized in document analysis to extract the semantic information and obtain descriptive topics. However, there are two problems that may affect their applications. One is that common words shared among all documents with low representational meaning may reduce the representation ability of learned topics. The other is introducing supervision information to hierarchical topic models to fully utilize the side information of documents that is difficult. To address these problems, in this article, we first propose deep diverse latent Dirichlet allocation (DDLDA), a deep hierarchical topic model that can yield more meaningful semantic topics with less common and meaningless words by introducing shared topics. Moreover, we develop a variational inference network for DDLDA, which helps us to further generalize DDLDA to a supervised deep topic model called max-margin DDLDA (mmDDLDA) by employing max-margin principle as the classification criterion. Compared to DDLDA, mmDDLDA can discover more discriminative topical representations. In addition, a continual hybrid method with stochastic-gradient MCMC and variational inference is put forward for deep latent Dirichlet allocation (DLDA)-based models to make them more practical in real-world applications. The experimental results demonstrate that DDLDA and mmDDLDA are more efficient than existing unsupervised and supervised topic models in discovering highly discriminative topic representations and achieving higher classification accuracy. Meanwhile, DLDA and our proposed models trained by the proposed continual learning approach cannot only show good performance on preventing catastrophic forgetting but also fit the evolving new tasks well." @default.
- W3136237185 created "2021-03-29" @default.
- W3136237185 creator A5023566999 @default.
- W3136237185 creator A5025477117 @default.
- W3136237185 creator A5043782065 @default.
- W3136237185 creator A5049341927 @default.
- W3136237185 creator A5051532783 @default.
- W3136237185 creator A5080886129 @default.
- W3136237185 creator A5081337604 @default.
- W3136237185 date "2022-07-01" @default.
- W3136237185 modified "2023-10-18" @default.
- W3136237185 title "Max-Margin Deep Diverse Latent Dirichlet Allocation With Continual Learning" @default.
- W3136237185 cites W1494474274 @default.
- W3136237185 cites W1584431645 @default.
- W3136237185 cites W1970089434 @default.
- W3136237185 cites W1976496742 @default.
- W3136237185 cites W2001975024 @default.
- W3136237185 cites W2059503458 @default.
- W3136237185 cites W2101101940 @default.
- W3136237185 cites W2171911691 @default.
- W3136237185 cites W2560647685 @default.
- W3136237185 cites W2963860678 @default.
- W3136237185 cites W2963921497 @default.
- W3136237185 cites W2964189064 @default.
- W3136237185 doi "https://doi.org/10.1109/tcyb.2020.3044915" @default.
- W3136237185 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33729964" @default.
- W3136237185 hasPublicationYear "2022" @default.
- W3136237185 type Work @default.
- W3136237185 sameAs 3136237185 @default.
- W3136237185 citedByCount "0" @default.
- W3136237185 crossrefType "journal-article" @default.
- W3136237185 hasAuthorship W3136237185A5023566999 @default.
- W3136237185 hasAuthorship W3136237185A5025477117 @default.
- W3136237185 hasAuthorship W3136237185A5043782065 @default.
- W3136237185 hasAuthorship W3136237185A5049341927 @default.
- W3136237185 hasAuthorship W3136237185A5051532783 @default.
- W3136237185 hasAuthorship W3136237185A5080886129 @default.
- W3136237185 hasAuthorship W3136237185A5081337604 @default.
- W3136237185 hasConcept C108583219 @default.
- W3136237185 hasConcept C119857082 @default.
- W3136237185 hasConcept C138885662 @default.
- W3136237185 hasConcept C154945302 @default.
- W3136237185 hasConcept C171686336 @default.
- W3136237185 hasConcept C17744445 @default.
- W3136237185 hasConcept C199539241 @default.
- W3136237185 hasConcept C2776214188 @default.
- W3136237185 hasConcept C2776359362 @default.
- W3136237185 hasConcept C41008148 @default.
- W3136237185 hasConcept C41895202 @default.
- W3136237185 hasConcept C49937458 @default.
- W3136237185 hasConcept C500882744 @default.
- W3136237185 hasConcept C7149132 @default.
- W3136237185 hasConcept C774472 @default.
- W3136237185 hasConcept C94625758 @default.
- W3136237185 hasConcept C97931131 @default.
- W3136237185 hasConceptScore W3136237185C108583219 @default.
- W3136237185 hasConceptScore W3136237185C119857082 @default.
- W3136237185 hasConceptScore W3136237185C138885662 @default.
- W3136237185 hasConceptScore W3136237185C154945302 @default.
- W3136237185 hasConceptScore W3136237185C171686336 @default.
- W3136237185 hasConceptScore W3136237185C17744445 @default.
- W3136237185 hasConceptScore W3136237185C199539241 @default.
- W3136237185 hasConceptScore W3136237185C2776214188 @default.
- W3136237185 hasConceptScore W3136237185C2776359362 @default.
- W3136237185 hasConceptScore W3136237185C41008148 @default.
- W3136237185 hasConceptScore W3136237185C41895202 @default.
- W3136237185 hasConceptScore W3136237185C49937458 @default.
- W3136237185 hasConceptScore W3136237185C500882744 @default.
- W3136237185 hasConceptScore W3136237185C7149132 @default.
- W3136237185 hasConceptScore W3136237185C774472 @default.
- W3136237185 hasConceptScore W3136237185C94625758 @default.
- W3136237185 hasConceptScore W3136237185C97931131 @default.
- W3136237185 hasFunder F4320321001 @default.
- W3136237185 hasFunder F4320327912 @default.
- W3136237185 hasIssue "7" @default.
- W3136237185 hasLocation W31362371851 @default.
- W3136237185 hasLocation W31362371852 @default.
- W3136237185 hasOpenAccess W3136237185 @default.
- W3136237185 hasPrimaryLocation W31362371851 @default.
- W3136237185 hasRelatedWork W2133568543 @default.
- W3136237185 hasRelatedWork W2159149403 @default.
- W3136237185 hasRelatedWork W2353457699 @default.
- W3136237185 hasRelatedWork W2511279186 @default.
- W3136237185 hasRelatedWork W2953238046 @default.
- W3136237185 hasRelatedWork W2963058055 @default.
- W3136237185 hasRelatedWork W3114039679 @default.
- W3136237185 hasRelatedWork W3136237185 @default.
- W3136237185 hasRelatedWork W4300631627 @default.
- W3136237185 hasRelatedWork W4312197973 @default.
- W3136237185 hasVolume "52" @default.
- W3136237185 isParatext "false" @default.
- W3136237185 isRetracted "false" @default.
- W3136237185 magId "3136237185" @default.
- W3136237185 workType "article" @default.