Matches in SemOpenAlex for { <https://semopenalex.org/work/W3080994088> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3080994088 abstract "This paper develops the Correlation Networks (CorNet) architecture for the extreme multi-label text classification (XMTC) task, where the objective is to tag an input text sequence with the most relevant subset of labels from an extremely large label set. XMTC can be found in many real-world applications, such as document tagging and product annotation. Recently, deep learning models have achieved outstanding performances in XMTC tasks. However, these deep XMTC models ignore the useful correlation information among different labels. CorNet addresses this limitation by adding an extra CorNet module at the prediction layer of a deep model, which is able to learn label correlations, enhance raw label predictions with correlation knowledge and output augmented label predictions. We show that CorNet can be easily integrated with deep XMTC models and generalize effectively across different datasets. We further demonstrate that CorNet can bring significant improvements over the existing deep XMTC models in terms of both performance and convergence rate. The models and datasets are available at: https://github.com/XunGuangxu/CorNet." @default.
- W3080994088 created "2020-09-01" @default.
- W3080994088 creator A5013588572 @default.
- W3080994088 creator A5021218766 @default.
- W3080994088 creator A5021740848 @default.
- W3080994088 creator A5048238468 @default.
- W3080994088 date "2020-08-20" @default.
- W3080994088 modified "2023-10-17" @default.
- W3080994088 title "Correlation Networks for Extreme Multi-label Text Classification" @default.
- W3080994088 cites W1781770377 @default.
- W3080994088 cites W1834987204 @default.
- W3080994088 cites W1981208470 @default.
- W3080994088 cites W2061873838 @default.
- W3080994088 cites W2068074736 @default.
- W3080994088 cites W2194775991 @default.
- W3080994088 cites W2362855512 @default.
- W3080994088 cites W2520348554 @default.
- W3080994088 cites W2739996966 @default.
- W3080994088 cites W2740139069 @default.
- W3080994088 cites W2743021690 @default.
- W3080994088 cites W2744007523 @default.
- W3080994088 cites W2744136723 @default.
- W3080994088 cites W2788125153 @default.
- W3080994088 cites W2954433047 @default.
- W3080994088 doi "https://doi.org/10.1145/3394486.3403151" @default.
- W3080994088 hasPublicationYear "2020" @default.
- W3080994088 type Work @default.
- W3080994088 sameAs 3080994088 @default.
- W3080994088 citedByCount "20" @default.
- W3080994088 countsByYear W30809940882021 @default.
- W3080994088 countsByYear W30809940882022 @default.
- W3080994088 countsByYear W30809940882023 @default.
- W3080994088 crossrefType "proceedings-article" @default.
- W3080994088 hasAuthorship W3080994088A5013588572 @default.
- W3080994088 hasAuthorship W3080994088A5021218766 @default.
- W3080994088 hasAuthorship W3080994088A5021740848 @default.
- W3080994088 hasAuthorship W3080994088A5048238468 @default.
- W3080994088 hasBestOaLocation W30809940881 @default.
- W3080994088 hasConcept C108583219 @default.
- W3080994088 hasConcept C117220453 @default.
- W3080994088 hasConcept C119857082 @default.
- W3080994088 hasConcept C127413603 @default.
- W3080994088 hasConcept C154945302 @default.
- W3080994088 hasConcept C177264268 @default.
- W3080994088 hasConcept C199360897 @default.
- W3080994088 hasConcept C201995342 @default.
- W3080994088 hasConcept C2524010 @default.
- W3080994088 hasConcept C2776321320 @default.
- W3080994088 hasConcept C2776482837 @default.
- W3080994088 hasConcept C2780451532 @default.
- W3080994088 hasConcept C33923547 @default.
- W3080994088 hasConcept C41008148 @default.
- W3080994088 hasConcept C90673727 @default.
- W3080994088 hasConceptScore W3080994088C108583219 @default.
- W3080994088 hasConceptScore W3080994088C117220453 @default.
- W3080994088 hasConceptScore W3080994088C119857082 @default.
- W3080994088 hasConceptScore W3080994088C127413603 @default.
- W3080994088 hasConceptScore W3080994088C154945302 @default.
- W3080994088 hasConceptScore W3080994088C177264268 @default.
- W3080994088 hasConceptScore W3080994088C199360897 @default.
- W3080994088 hasConceptScore W3080994088C201995342 @default.
- W3080994088 hasConceptScore W3080994088C2524010 @default.
- W3080994088 hasConceptScore W3080994088C2776321320 @default.
- W3080994088 hasConceptScore W3080994088C2776482837 @default.
- W3080994088 hasConceptScore W3080994088C2780451532 @default.
- W3080994088 hasConceptScore W3080994088C33923547 @default.
- W3080994088 hasConceptScore W3080994088C41008148 @default.
- W3080994088 hasConceptScore W3080994088C90673727 @default.
- W3080994088 hasFunder F4320306076 @default.
- W3080994088 hasLocation W30809940881 @default.
- W3080994088 hasOpenAccess W3080994088 @default.
- W3080994088 hasPrimaryLocation W30809940881 @default.
- W3080994088 hasRelatedWork W2947809439 @default.
- W3080994088 hasRelatedWork W3014300295 @default.
- W3080994088 hasRelatedWork W3164822677 @default.
- W3080994088 hasRelatedWork W4223943233 @default.
- W3080994088 hasRelatedWork W4225161397 @default.
- W3080994088 hasRelatedWork W4250304930 @default.
- W3080994088 hasRelatedWork W4309045103 @default.
- W3080994088 hasRelatedWork W4312200629 @default.
- W3080994088 hasRelatedWork W4360585206 @default.
- W3080994088 hasRelatedWork W4364306694 @default.
- W3080994088 isParatext "false" @default.
- W3080994088 isRetracted "false" @default.
- W3080994088 magId "3080994088" @default.
- W3080994088 workType "article" @default.