FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3212936637> ?p ?o ?g. }

• W3212936637 abstract "Existing deep hierarchical topic models are able to extract semantically meaningful topics from a text corpus in an unsupervised manner and automatically organize them into a topic hierarchy. However, it is unclear how to incorporate prior beliefs such as knowledge graph to guide the learning of the topic hierarchy. To address this issue, we introduce TopicNet as a deep hierarchical topic model that can inject prior structural knowledge as an inductive bias to influence learning. TopicNet represents each topic as a Gaussian-distributed embedding vector, projects the topics of all layers into a shared embedding space, and explores both the symmetric and asymmetric similarities between Gaussian embedding vectors to incorporate prior semantic hierarchies. With an auto-encoding variational inference network, the model parameters are optimized by minimizing the evidence lower bound and a regularization term via stochastic gradient descent. Experiments on widely used benchmarks show that TopicNet outperforms related deep topic models on discovering deeper interpretable topics and mining better document~representations." @default.
• W3212936637 created "2021-11-22" @default.
• W3212936637 creator A5010394308 @default.
• W3212936637 creator A5040147917 @default.
• W3212936637 creator A5052158421 @default.
• W3212936637 creator A5067483347 @default.
• W3212936637 creator A5083126177 @default.
• W3212936637 creator A5086002590 @default.
• W3212936637 date "2021-10-27" @default.
• W3212936637 modified "2023-10-18" @default.
• W3212936637 title "TopicNet: Semantic Graph-Guided Topic Discovery" @default.
• W3212936637 cites W1522301498 @default.
• W3212936637 cites W1880262756 @default.
• W3212936637 cites W2005564522 @default.
• W3212936637 cites W2081580037 @default.
• W3212936637 cites W2127265454 @default.
• W3212936637 cites W2150286230 @default.
• W3212936637 cites W2151531457 @default.
• W3212936637 cites W2157364932 @default.
• W3212936637 cites W2159426623 @default.
• W3212936637 cites W2170678468 @default.
• W3212936637 cites W2172888184 @default.
• W3212936637 cites W2187089797 @default.
• W3212936637 cites W2187625046 @default.
• W3212936637 cites W2216511711 @default.
• W3212936637 cites W2251582277 @default.
• W3212936637 cites W2399880602 @default.
• W3212936637 cites W2465309725 @default.
• W3212936637 cites W2529448042 @default.
• W3212936637 cites W2560512785 @default.
• W3212936637 cites W2570343428 @default.
• W3212936637 cites W2585828887 @default.
• W3212936637 cites W2594057160 @default.
• W3212936637 cites W2624543814 @default.
• W3212936637 cites W2788195014 @default.
• W3212936637 cites W2799174950 @default.
• W3212936637 cites W2899112946 @default.
• W3212936637 cites W2946781947 @default.
• W3212936637 cites W2951004968 @default.
• W3212936637 cites W2952478253 @default.
• W3212936637 cites W2962915345 @default.
• W3212936637 cites W2963135265 @default.
• W3212936637 cites W2963341956 @default.
• W3212936637 cites W2963799213 @default.
• W3212936637 cites W2964094663 @default.
• W3212936637 cites W3035938556 @default.
• W3212936637 cites W3045464143 @default.
• W3212936637 cites W3103576111 @default.
• W3212936637 cites W3105538385 @default.
• W3212936637 cites W3106176216 @default.
• W3212936637 cites W3166402665 @default.
• W3212936637 cites W3171661673 @default.
• W3212936637 doi "https://doi.org/10.48550/arxiv.2110.14286" @default.
• W3212936637 hasPublicationYear "2021" @default.
• W3212936637 type Work @default.
• W3212936637 sameAs 3212936637 @default.
• W3212936637 citedByCount "0" @default.
• W3212936637 crossrefType "posted-content" @default.
• W3212936637 hasAuthorship W3212936637A5010394308 @default.
• W3212936637 hasAuthorship W3212936637A5040147917 @default.
• W3212936637 hasAuthorship W3212936637A5052158421 @default.
• W3212936637 hasAuthorship W3212936637A5067483347 @default.
• W3212936637 hasAuthorship W3212936637A5083126177 @default.
• W3212936637 hasAuthorship W3212936637A5086002590 @default.
• W3212936637 hasBestOaLocation W32129366371 @default.
• W3212936637 hasConcept C108583219 @default.
• W3212936637 hasConcept C119857082 @default.
• W3212936637 hasConcept C121332964 @default.
• W3212936637 hasConcept C132525143 @default.
• W3212936637 hasConcept C13336665 @default.
• W3212936637 hasConcept C153258448 @default.
• W3212936637 hasConcept C154945302 @default.
• W3212936637 hasConcept C162324750 @default.
• W3212936637 hasConcept C163716315 @default.
• W3212936637 hasConcept C171686336 @default.
• W3212936637 hasConcept C204321447 @default.
• W3212936637 hasConcept C2524010 @default.
• W3212936637 hasConcept C2776135515 @default.
• W3212936637 hasConcept C2776214188 @default.
• W3212936637 hasConcept C2986420190 @default.
• W3212936637 hasConcept C2987255567 @default.
• W3212936637 hasConcept C31170391 @default.
• W3212936637 hasConcept C33923547 @default.
• W3212936637 hasConcept C34447519 @default.
• W3212936637 hasConcept C41008148 @default.
• W3212936637 hasConcept C41608201 @default.
• W3212936637 hasConcept C50644808 @default.
• W3212936637 hasConcept C62520636 @default.
• W3212936637 hasConcept C80444323 @default.
• W3212936637 hasConceptScore W3212936637C108583219 @default.
• W3212936637 hasConceptScore W3212936637C119857082 @default.
• W3212936637 hasConceptScore W3212936637C121332964 @default.
• W3212936637 hasConceptScore W3212936637C132525143 @default.
• W3212936637 hasConceptScore W3212936637C13336665 @default.
• W3212936637 hasConceptScore W3212936637C153258448 @default.
• W3212936637 hasConceptScore W3212936637C154945302 @default.
• W3212936637 hasConceptScore W3212936637C162324750 @default.
• W3212936637 hasConceptScore W3212936637C163716315 @default.
• W3212936637 hasConceptScore W3212936637C171686336 @default.
• W3212936637 hasConceptScore W3212936637C204321447 @default.

• next