FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048922981> ?p ?o ?g. }

• W3048922981 endingPage "91" @default.
• W3048922981 startingPage "79" @default.
• W3048922981 abstract "As one of the prevalent topic mining methods, neural topic modeling has attracted a lot of interests due to the advantages of low training costs and strong generalisation abilities. However, the existing neural topic models may suffer from the feature sparsity problem when applied to short texts, due to the lack of context in each message. To alleviate this issue, we propose a Context Reinforced Neural Topic Model (CRNTM), whose characteristics can be summarized as follows. First, by assuming that each short text covers only a few salient topics, the proposed CRNTM infers the topic for each word in a narrow range. Second, our model exploits pre-trained word embeddings by treating topics as multivariate Gaussian distributions or Gaussian mixture distributions in the embedding space. Extensive experiments on two benchmark short corpora validate the effectiveness of the proposed model on both topic discovery and text classification." @default.
• W3048922981 created "2020-08-18" @default.
• W3048922981 creator A5049321721 @default.
• W3048922981 creator A5058291454 @default.
• W3048922981 creator A5076913483 @default.
• W3048922981 creator A5077663627 @default.
• W3048922981 creator A5087425964 @default.
• W3048922981 date "2022-08-01" @default.
• W3048922981 modified "2023-10-14" @default.
• W3048922981 title "Context reinforced neural topic modeling over short texts" @default.
• W3048922981 cites W2001082470 @default.
• W3048922981 cites W2048195127 @default.
• W3048922981 cites W2520861906 @default.
• W3048922981 cites W2686419387 @default.
• W3048922981 cites W2739283086 @default.
• W3048922981 cites W2765472318 @default.
• W3048922981 cites W2765668510 @default.
• W3048922981 cites W2789456849 @default.
• W3048922981 cites W2794393856 @default.
• W3048922981 cites W2799080304 @default.
• W3048922981 cites W2801961685 @default.
• W3048922981 cites W2910376060 @default.
• W3048922981 cites W2981018152 @default.
• W3048922981 cites W2996478248 @default.
• W3048922981 cites W3010923242 @default.
• W3048922981 cites W3032589391 @default.
• W3048922981 doi "https://doi.org/10.1016/j.ins.2022.05.098" @default.
• W3048922981 hasPublicationYear "2022" @default.
• W3048922981 type Work @default.
• W3048922981 sameAs 3048922981 @default.
• W3048922981 citedByCount "8" @default.
• W3048922981 countsByYear W30489229812021 @default.
• W3048922981 countsByYear W30489229812023 @default.
• W3048922981 crossrefType "journal-article" @default.
• W3048922981 hasAuthorship W3048922981A5049321721 @default.
• W3048922981 hasAuthorship W3048922981A5058291454 @default.
• W3048922981 hasAuthorship W3048922981A5076913483 @default.
• W3048922981 hasAuthorship W3048922981A5077663627 @default.
• W3048922981 hasAuthorship W3048922981A5087425964 @default.
• W3048922981 hasBestOaLocation W30489229812 @default.
• W3048922981 hasConcept C119857082 @default.
• W3048922981 hasConcept C121332964 @default.
• W3048922981 hasConcept C13280743 @default.
• W3048922981 hasConcept C138885662 @default.
• W3048922981 hasConcept C151730666 @default.
• W3048922981 hasConcept C154945302 @default.
• W3048922981 hasConcept C159985019 @default.
• W3048922981 hasConcept C161584116 @default.
• W3048922981 hasConcept C163716315 @default.
• W3048922981 hasConcept C165696696 @default.
• W3048922981 hasConcept C171686336 @default.
• W3048922981 hasConcept C185798385 @default.
• W3048922981 hasConcept C192562407 @default.
• W3048922981 hasConcept C204321447 @default.
• W3048922981 hasConcept C204323151 @default.
• W3048922981 hasConcept C205649164 @default.
• W3048922981 hasConcept C2524010 @default.
• W3048922981 hasConcept C26517878 @default.
• W3048922981 hasConcept C2776401178 @default.
• W3048922981 hasConcept C2777462759 @default.
• W3048922981 hasConcept C2779343474 @default.
• W3048922981 hasConcept C2780719617 @default.
• W3048922981 hasConcept C33923547 @default.
• W3048922981 hasConcept C38652104 @default.
• W3048922981 hasConcept C41008148 @default.
• W3048922981 hasConcept C41608201 @default.
• W3048922981 hasConcept C41895202 @default.
• W3048922981 hasConcept C50644808 @default.
• W3048922981 hasConcept C62520636 @default.
• W3048922981 hasConcept C86803240 @default.
• W3048922981 hasConcept C90805587 @default.
• W3048922981 hasConceptScore W3048922981C119857082 @default.
• W3048922981 hasConceptScore W3048922981C121332964 @default.
• W3048922981 hasConceptScore W3048922981C13280743 @default.
• W3048922981 hasConceptScore W3048922981C138885662 @default.
• W3048922981 hasConceptScore W3048922981C151730666 @default.
• W3048922981 hasConceptScore W3048922981C154945302 @default.
• W3048922981 hasConceptScore W3048922981C159985019 @default.
• W3048922981 hasConceptScore W3048922981C161584116 @default.
• W3048922981 hasConceptScore W3048922981C163716315 @default.
• W3048922981 hasConceptScore W3048922981C165696696 @default.
• W3048922981 hasConceptScore W3048922981C171686336 @default.
• W3048922981 hasConceptScore W3048922981C185798385 @default.
• W3048922981 hasConceptScore W3048922981C192562407 @default.
• W3048922981 hasConceptScore W3048922981C204321447 @default.
• W3048922981 hasConceptScore W3048922981C204323151 @default.
• W3048922981 hasConceptScore W3048922981C205649164 @default.
• W3048922981 hasConceptScore W3048922981C2524010 @default.
• W3048922981 hasConceptScore W3048922981C26517878 @default.
• W3048922981 hasConceptScore W3048922981C2776401178 @default.
• W3048922981 hasConceptScore W3048922981C2777462759 @default.
• W3048922981 hasConceptScore W3048922981C2779343474 @default.
• W3048922981 hasConceptScore W3048922981C2780719617 @default.
• W3048922981 hasConceptScore W3048922981C33923547 @default.
• W3048922981 hasConceptScore W3048922981C38652104 @default.
• W3048922981 hasConceptScore W3048922981C41008148 @default.
• W3048922981 hasConceptScore W3048922981C41608201 @default.
• W3048922981 hasConceptScore W3048922981C41895202 @default.

• next