FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226055852> ?p ?o ?g. }

• W4226055852 endingPage "358" @default.
• W4226055852 startingPage "343" @default.
• W4226055852 abstract "Deep learning oriented named entity recognition (DNER) has gradually become the paradigm of knowledge discovery, which greatly promotes domain intelligence. However, the activation function of DNER fails to treat gradient vanishing, no negative output or non-differentiable existence, which may impede the exploration of knowledge due to the omission and incomplete representation of the latent semantic. To break through the dilemma, we present a novel activation function termed KDAC. Detailly, KDAC is an aggregation function with multiple conversion modes. The backbone is the interaction between exponent and linearity, and the both ends are extended through adaptive linear divergence, which can surmount the gradient vanishing and no negative output. Crucially, the non-differentiable points can be alerted and eliminated by an approximate smoothing algorithm. KDAC has a series of brilliant properties, such as nonlinear, stable near-linear transformation and derivative, as well as dynamic style, etc. We perform experiments based on BERT-BiLSTM-CNN-CRF model on six benchmark datasets containing different domain knowledge, such as Weibo, Clinical, E-commerce, Resume, HAZOP and People's daily. The evaluation results show that KDAC is advanced and effective, and can provide more generalized activation to stimulate the performance of DNER. We hope that KDAC can be exploited as a promising activation function to devote itself to the construction of knowledge." @default.
• W4226055852 created "2022-05-05" @default.
• W4226055852 creator A5006064743 @default.
• W4226055852 creator A5006513586 @default.
• W4226055852 creator A5030844655 @default.
• W4226055852 creator A5079253718 @default.
• W4226055852 date "2022-08-01" @default.
• W4226055852 modified "2023-10-01" @default.
• W4226055852 title "Why KDAC? A general activation function for knowledge discovery" @default.
• W4226055852 cites W1677182931 @default.
• W4226055852 cites W1987803244 @default.
• W4226055852 cites W1992282307 @default.
• W4226055852 cites W2013563212 @default.
• W4226055852 cites W2069763315 @default.
• W4226055852 cites W2102184039 @default.
• W4226055852 cites W2793180589 @default.
• W4226055852 cites W2902935192 @default.
• W4226055852 cites W2903381540 @default.
• W4226055852 cites W2962904552 @default.
• W4226055852 cites W2963009098 @default.
• W4226055852 cites W2971668428 @default.
• W4226055852 cites W2972528933 @default.
• W4226055852 cites W2981986127 @default.
• W4226055852 cites W2992983008 @default.
• W4226055852 cites W3014451614 @default.
• W4226055852 cites W3023212902 @default.
• W4226055852 cites W3023484593 @default.
• W4226055852 cites W3023618320 @default.
• W4226055852 cites W3037333170 @default.
• W4226055852 cites W3045156229 @default.
• W4226055852 cites W3046023260 @default.
• W4226055852 cites W3087374654 @default.
• W4226055852 cites W3093291461 @default.
• W4226055852 cites W3096121092 @default.
• W4226055852 cites W3101520866 @default.
• W4226055852 cites W3105158372 @default.
• W4226055852 cites W3111772703 @default.
• W4226055852 cites W3116443551 @default.
• W4226055852 cites W3117168610 @default.
• W4226055852 cites W3117453207 @default.
• W4226055852 cites W3117568220 @default.
• W4226055852 cites W3123194504 @default.
• W4226055852 cites W3126661169 @default.
• W4226055852 cites W3134817226 @default.
• W4226055852 cites W3136058829 @default.
• W4226055852 cites W3137156863 @default.
• W4226055852 cites W3137401156 @default.
• W4226055852 cites W3137747590 @default.
• W4226055852 cites W3138408498 @default.
• W4226055852 cites W3138523474 @default.
• W4226055852 cites W3152219206 @default.
• W4226055852 cites W3158376750 @default.
• W4226055852 cites W3162596511 @default.
• W4226055852 cites W3163600202 @default.
• W4226055852 cites W3174889011 @default.
• W4226055852 cites W3175058671 @default.
• W4226055852 cites W3177143834 @default.
• W4226055852 cites W3180847413 @default.
• W4226055852 cites W3181047556 @default.
• W4226055852 cites W3196719896 @default.
• W4226055852 cites W3203177300 @default.
• W4226055852 cites W3206914982 @default.
• W4226055852 cites W3213591530 @default.
• W4226055852 cites W3217227808 @default.
• W4226055852 cites W4200150102 @default.
• W4226055852 doi "https://doi.org/10.1016/j.neucom.2022.06.019" @default.
• W4226055852 hasPublicationYear "2022" @default.
• W4226055852 type Work @default.
• W4226055852 citedByCount "3" @default.
• W4226055852 countsByYear W42260558522023 @default.
• W4226055852 crossrefType "journal-article" @default.
• W4226055852 hasAuthorship W4226055852A5006064743 @default.
• W4226055852 hasAuthorship W4226055852A5006513586 @default.
• W4226055852 hasAuthorship W4226055852A5030844655 @default.
• W4226055852 hasAuthorship W4226055852A5079253718 @default.
• W4226055852 hasBestOaLocation W42260558522 @default.
• W4226055852 hasConcept C11413529 @default.
• W4226055852 hasConcept C13280743 @default.
• W4226055852 hasConcept C134306372 @default.
• W4226055852 hasConcept C14036430 @default.
• W4226055852 hasConcept C154945302 @default.
• W4226055852 hasConcept C17744445 @default.
• W4226055852 hasConcept C185798385 @default.
• W4226055852 hasConcept C199539241 @default.
• W4226055852 hasConcept C202444582 @default.
• W4226055852 hasConcept C202615002 @default.
• W4226055852 hasConcept C205649164 @default.
• W4226055852 hasConcept C207685749 @default.
• W4226055852 hasConcept C2776359362 @default.
• W4226055852 hasConcept C31972630 @default.
• W4226055852 hasConcept C33923547 @default.
• W4226055852 hasConcept C36503486 @default.
• W4226055852 hasConcept C3770464 @default.
• W4226055852 hasConcept C38365724 @default.
• W4226055852 hasConcept C41008148 @default.
• W4226055852 hasConcept C50644808 @default.
• W4226055852 hasConcept C78458016 @default.
• W4226055852 hasConcept C86803240 @default.

• next