FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048479901> ?p ?o ?g. }

• W3048479901 abstract "Neural network-based approaches have become the driven forces for Natural Language Processing (NLP) tasks. Conventionally, there are two mainstream neural architectures for NLP tasks: the recurrent neural network (RNN) and the convolution neural network (ConvNet). RNNs are good at modeling long-term dependencies over input texts, but preclude parallel computation. ConvNets do not have memory capability and it has to model sequential data as un-ordered features. Therefore, ConvNets fail to learn sequential dependencies over the input texts, but it is able to carry out high-efficient parallel computation. As each neural architecture, such as RNN and ConvNets, has its own pro and con, integration of different architectures is assumed to be able to enrich the semantic representation of texts, thus enhance the performance of NLP tasks. However, few investigation explores the reconciliation of these seemingly incompatible architectures. To address this issue, we propose a hybrid architecture based on a novel hierarchical multi-granularity attention mechanism, named Multi-granularity Attention-based Hybrid Neural Network (MahNN). The attention mechanism is to assign different weights to different parts of the input sequence to increase the computation efficiency and performance of neural models. In MahNN, two types of attentions are introduced: the syntactical attention and the semantical attention. The syntactical attention computes the importance of the syntactic elements (such as words or sentence) at the lower symbolic level and the semantical attention is used to compute the importance of the embedded space dimension corresponding to the upper latent semantics. We adopt the text classification as an exemplifying way to illustrate the ability of MahNN to understand texts." @default.
• W3048479901 created "2020-08-18" @default.
• W3048479901 creator A5024389645 @default.
• W3048479901 creator A5039580757 @default.
• W3048479901 creator A5055090719 @default.
• W3048479901 creator A5082414716 @default.
• W3048479901 creator A5083664918 @default.
• W3048479901 date "2020-08-12" @default.
• W3048479901 modified "2023-09-26" @default.
• W3048479901 title "Text Classification based on Multi-granularity Attention Hybrid Neural Network" @default.
• W3048479901 cites W1784932861 @default.
• W3048479901 cites W1889268436 @default.
• W3048479901 cites W1894439495 @default.
• W3048479901 cites W1902237438 @default.
• W3048479901 cites W1924770834 @default.
• W3048479901 cites W1965102691 @default.
• W3048479901 cites W1970861901 @default.
• W3048479901 cites W2012899881 @default.
• W3048479901 cites W2041834949 @default.
• W3048479901 cites W2064675550 @default.
• W3048479901 cites W2071198194 @default.
• W3048479901 cites W2107878631 @default.
• W3048479901 cites W2119408773 @default.
• W3048479901 cites W2120615054 @default.
• W3048479901 cites W2131744502 @default.
• W3048479901 cites W2132339004 @default.
• W3048479901 cites W2153579005 @default.
• W3048479901 cites W2154359981 @default.
• W3048479901 cites W2157331557 @default.
• W3048479901 cites W2215770505 @default.
• W3048479901 cites W2250966211 @default.
• W3048479901 cites W2251143283 @default.
• W3048479901 cites W2251939518 @default.
• W3048479901 cites W2265846598 @default.
• W3048479901 cites W2468328197 @default.
• W3048479901 cites W2468476969 @default.
• W3048479901 cites W2470673105 @default.
• W3048479901 cites W2492847349 @default.
• W3048479901 cites W2512205159 @default.
• W3048479901 cites W2532073801 @default.
• W3048479901 cites W2585540825 @default.
• W3048479901 cites W2742940593 @default.
• W3048479901 cites W2751185861 @default.
• W3048479901 cites W2752655323 @default.
• W3048479901 cites W2770626724 @default.
• W3048479901 cites W2784579605 @default.
• W3048479901 cites W2786435373 @default.
• W3048479901 cites W2792602623 @default.
• W3048479901 cites W2881883021 @default.
• W3048479901 cites W2890177507 @default.
• W3048479901 cites W2899887039 @default.
• W3048479901 cites W2901633434 @default.
• W3048479901 cites W2919115771 @default.
• W3048479901 cites W2949257818 @default.
• W3048479901 cites W2949541494 @default.
• W3048479901 cites W2949888546 @default.
• W3048479901 cites W2963012544 @default.
• W3048479901 cites W2963403868 @default.
• W3048479901 cites W2964308564 @default.
• W3048479901 cites W35527955 @default.
• W3048479901 cites W71795751 @default.
• W3048479901 doi "https://doi.org/10.48550/arxiv.2008.05282" @default.
• W3048479901 hasPublicationYear "2020" @default.
• W3048479901 type Work @default.
• W3048479901 sameAs 3048479901 @default.
• W3048479901 citedByCount "0" @default.
• W3048479901 crossrefType "posted-content" @default.
• W3048479901 hasAuthorship W3048479901A5024389645 @default.
• W3048479901 hasAuthorship W3048479901A5039580757 @default.
• W3048479901 hasAuthorship W3048479901A5055090719 @default.
• W3048479901 hasAuthorship W3048479901A5082414716 @default.
• W3048479901 hasAuthorship W3048479901A5083664918 @default.
• W3048479901 hasBestOaLocation W30484799011 @default.
• W3048479901 hasConcept C11413529 @default.
• W3048479901 hasConcept C119857082 @default.
• W3048479901 hasConcept C147168706 @default.
• W3048479901 hasConcept C154945302 @default.
• W3048479901 hasConcept C177774035 @default.
• W3048479901 hasConcept C184337299 @default.
• W3048479901 hasConcept C199360897 @default.
• W3048479901 hasConcept C202444582 @default.
• W3048479901 hasConcept C204321447 @default.
• W3048479901 hasConcept C2777530160 @default.
• W3048479901 hasConcept C33676613 @default.
• W3048479901 hasConcept C33923547 @default.
• W3048479901 hasConcept C41008148 @default.
• W3048479901 hasConcept C45374587 @default.
• W3048479901 hasConcept C50644808 @default.
• W3048479901 hasConceptScore W3048479901C11413529 @default.
• W3048479901 hasConceptScore W3048479901C119857082 @default.
• W3048479901 hasConceptScore W3048479901C147168706 @default.
• W3048479901 hasConceptScore W3048479901C154945302 @default.
• W3048479901 hasConceptScore W3048479901C177774035 @default.
• W3048479901 hasConceptScore W3048479901C184337299 @default.
• W3048479901 hasConceptScore W3048479901C199360897 @default.
• W3048479901 hasConceptScore W3048479901C202444582 @default.
• W3048479901 hasConceptScore W3048479901C204321447 @default.
• W3048479901 hasConceptScore W3048479901C2777530160 @default.
• W3048479901 hasConceptScore W3048479901C33676613 @default.
• W3048479901 hasConceptScore W3048479901C33923547 @default.

• next