FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890521812> ?p ?o ?g. }

• W2890521812 abstract "Deep neural networks reach state-of-the-art performance for wide range of natural language processing, computer vision and speech applications. Yet, one of the biggest challenges is running these complex networks on devices such as mobile phones or smart watches with tiny memory footprint and low computational capacity. We propose on-device Self-Governing Neural Networks (SGNNs), which learn compact projection vectors with local sensitive hashing. The key advantage of SGNNs over existing work is that they surmount the need for pre-trained word embeddings and complex networks with huge parameters. We conduct extensive evaluation on dialog act classification and show significant improvement over state-of-the-art results. Our findings show that SGNNs are effective at capturing low-dimensional semantic text representations, while maintaining high accuracy." @default.
• W2890521812 created "2018-09-27" @default.
• W2890521812 creator A5007532004 @default.
• W2890521812 creator A5090605375 @default.
• W2890521812 date "2018-01-01" @default.
• W2890521812 modified "2023-09-25" @default.
• W2890521812 title "Self-Governing Neural Networks for On-Device Short Text Classification" @default.
• W2890521812 cites W104184427 @default.
• W2890521812 cites W1503312748 @default.
• W2890521812 cites W1532325895 @default.
• W2890521812 cites W1591607137 @default.
• W2890521812 cites W1887499533 @default.
• W2890521812 cites W2012833704 @default.
• W2890521812 cites W2028486550 @default.
• W2890521812 cites W2102028293 @default.
• W2890521812 cites W2118365837 @default.
• W2890521812 cites W2130942839 @default.
• W2890521812 cites W2163605009 @default.
• W2890521812 cites W2166637769 @default.
• W2890521812 cites W2279098554 @default.
• W2890521812 cites W2573626026 @default.
• W2890521812 cites W2599207826 @default.
• W2890521812 cites W2739515247 @default.
• W2890521812 cites W2741802726 @default.
• W2890521812 cites W2774523402 @default.
• W2890521812 cites W2775769009 @default.
• W2890521812 cites W2783819585 @default.
• W2890521812 cites W2950444459 @default.
• W2890521812 cites W2962803631 @default.
• W2890521812 cites W2963263347 @default.
• W2890521812 cites W2964331270 @default.
• W2890521812 doi "https://doi.org/10.18653/v1/d18-1092" @default.
• W2890521812 hasPublicationYear "2018" @default.
• W2890521812 type Work @default.
• W2890521812 sameAs 2890521812 @default.
• W2890521812 citedByCount "8" @default.
• W2890521812 countsByYear W28905218122019 @default.
• W2890521812 countsByYear W28905218122020 @default.
• W2890521812 countsByYear W28905218122021 @default.
• W2890521812 countsByYear W28905218122022 @default.
• W2890521812 countsByYear W28905218122023 @default.
• W2890521812 crossrefType "proceedings-article" @default.
• W2890521812 hasAuthorship W2890521812A5007532004 @default.
• W2890521812 hasAuthorship W2890521812A5090605375 @default.
• W2890521812 hasBestOaLocation W28905218121 @default.
• W2890521812 hasConcept C111919701 @default.
• W2890521812 hasConcept C11413529 @default.
• W2890521812 hasConcept C119857082 @default.
• W2890521812 hasConcept C132943942 @default.
• W2890521812 hasConcept C136764020 @default.
• W2890521812 hasConcept C151730666 @default.
• W2890521812 hasConcept C154945302 @default.
• W2890521812 hasConcept C159985019 @default.
• W2890521812 hasConcept C173853756 @default.
• W2890521812 hasConcept C186967261 @default.
• W2890521812 hasConcept C192562407 @default.
• W2890521812 hasConcept C204323151 @default.
• W2890521812 hasConcept C26517878 @default.
• W2890521812 hasConcept C2984842247 @default.
• W2890521812 hasConcept C38652104 @default.
• W2890521812 hasConcept C41008148 @default.
• W2890521812 hasConcept C48103436 @default.
• W2890521812 hasConcept C50644808 @default.
• W2890521812 hasConcept C57493831 @default.
• W2890521812 hasConcept C74912251 @default.
• W2890521812 hasConcept C86803240 @default.
• W2890521812 hasConcept C99138194 @default.
• W2890521812 hasConceptScore W2890521812C111919701 @default.
• W2890521812 hasConceptScore W2890521812C11413529 @default.
• W2890521812 hasConceptScore W2890521812C119857082 @default.
• W2890521812 hasConceptScore W2890521812C132943942 @default.
• W2890521812 hasConceptScore W2890521812C136764020 @default.
• W2890521812 hasConceptScore W2890521812C151730666 @default.
• W2890521812 hasConceptScore W2890521812C154945302 @default.
• W2890521812 hasConceptScore W2890521812C159985019 @default.
• W2890521812 hasConceptScore W2890521812C173853756 @default.
• W2890521812 hasConceptScore W2890521812C186967261 @default.
• W2890521812 hasConceptScore W2890521812C192562407 @default.
• W2890521812 hasConceptScore W2890521812C204323151 @default.
• W2890521812 hasConceptScore W2890521812C26517878 @default.
• W2890521812 hasConceptScore W2890521812C2984842247 @default.
• W2890521812 hasConceptScore W2890521812C38652104 @default.
• W2890521812 hasConceptScore W2890521812C41008148 @default.
• W2890521812 hasConceptScore W2890521812C48103436 @default.
• W2890521812 hasConceptScore W2890521812C50644808 @default.
• W2890521812 hasConceptScore W2890521812C57493831 @default.
• W2890521812 hasConceptScore W2890521812C74912251 @default.
• W2890521812 hasConceptScore W2890521812C86803240 @default.
• W2890521812 hasConceptScore W2890521812C99138194 @default.
• W2890521812 hasLocation W28905218121 @default.
• W2890521812 hasOpenAccess W2890521812 @default.
• W2890521812 hasPrimaryLocation W28905218121 @default.
• W2890521812 hasRelatedWork W1862650538 @default.
• W2890521812 hasRelatedWork W1942955488 @default.
• W2890521812 hasRelatedWork W2030761633 @default.
• W2890521812 hasRelatedWork W2034940213 @default.
• W2890521812 hasRelatedWork W2352008582 @default.
• W2890521812 hasRelatedWork W3112569517 @default.
• W2890521812 hasRelatedWork W3163572252 @default.
• W2890521812 hasRelatedWork W4226338738 @default.

• next