Matches in SemOpenAlex for { <https://semopenalex.org/work/W3016689222> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W3016689222 abstract "Because self-attention captures long-distance features without generating sequence dependence, it has been widely used in machine translation and machine reading comprehension. However, there is a lack of research and exploration on self-attention in text classification research methods. This paper proposes a classification model based on Self-Attention, which applies the self-attention mechanism to text classification tasks reasonably. In addition, based on the self-attention model, we further propose a convolutional neural networks(CNN) based on the double-head attention mechanism. The experimental results show that the double-head attention-based convolutional neural networks (DHACNN) improves the classification accuracy and optimizes the test speed." @default.
- W3016689222 created "2020-04-24" @default.
- W3016689222 creator A5007168859 @default.
- W3016689222 creator A5033334483 @default.
- W3016689222 creator A5045296698 @default.
- W3016689222 date "2019-12-01" @default.
- W3016689222 modified "2023-09-27" @default.
- W3016689222 title "Double-Head Attention-Based Convolutional Neural Networks for Text Classification" @default.
- W3016689222 cites W2120615054 @default.
- W3016689222 cites W2250999640 @default.
- W3016689222 cites W2265846598 @default.
- W3016689222 cites W2402251768 @default.
- W3016689222 cites W2523325931 @default.
- W3016689222 cites W2618360053 @default.
- W3016689222 cites W2905072567 @default.
- W3016689222 cites W2908495650 @default.
- W3016689222 cites W2908570739 @default.
- W3016689222 cites W2963497309 @default.
- W3016689222 cites W2973935944 @default.
- W3016689222 cites W2985808369 @default.
- W3016689222 doi "https://doi.org/10.1109/ijcime49369.2019.00015" @default.
- W3016689222 hasPublicationYear "2019" @default.
- W3016689222 type Work @default.
- W3016689222 sameAs 3016689222 @default.
- W3016689222 citedByCount "0" @default.
- W3016689222 crossrefType "proceedings-article" @default.
- W3016689222 hasAuthorship W3016689222A5007168859 @default.
- W3016689222 hasAuthorship W3016689222A5033334483 @default.
- W3016689222 hasAuthorship W3016689222A5045296698 @default.
- W3016689222 hasConcept C114793014 @default.
- W3016689222 hasConcept C127313418 @default.
- W3016689222 hasConcept C153180895 @default.
- W3016689222 hasConcept C154945302 @default.
- W3016689222 hasConcept C204321447 @default.
- W3016689222 hasConcept C2780312720 @default.
- W3016689222 hasConcept C28490314 @default.
- W3016689222 hasConcept C41008148 @default.
- W3016689222 hasConcept C81363708 @default.
- W3016689222 hasConceptScore W3016689222C114793014 @default.
- W3016689222 hasConceptScore W3016689222C127313418 @default.
- W3016689222 hasConceptScore W3016689222C153180895 @default.
- W3016689222 hasConceptScore W3016689222C154945302 @default.
- W3016689222 hasConceptScore W3016689222C204321447 @default.
- W3016689222 hasConceptScore W3016689222C2780312720 @default.
- W3016689222 hasConceptScore W3016689222C28490314 @default.
- W3016689222 hasConceptScore W3016689222C41008148 @default.
- W3016689222 hasConceptScore W3016689222C81363708 @default.
- W3016689222 hasLocation W30166892221 @default.
- W3016689222 hasOpenAccess W3016689222 @default.
- W3016689222 hasPrimaryLocation W30166892221 @default.
- W3016689222 hasRelatedWork W2175746458 @default.
- W3016689222 hasRelatedWork W2732542196 @default.
- W3016689222 hasRelatedWork W2738221750 @default.
- W3016689222 hasRelatedWork W2760085659 @default.
- W3016689222 hasRelatedWork W2912288872 @default.
- W3016689222 hasRelatedWork W3012978760 @default.
- W3016689222 hasRelatedWork W3081496756 @default.
- W3016689222 hasRelatedWork W3093612317 @default.
- W3016689222 hasRelatedWork W4304820710 @default.
- W3016689222 hasRelatedWork W564581980 @default.
- W3016689222 isParatext "false" @default.
- W3016689222 isRetracted "false" @default.
- W3016689222 magId "3016689222" @default.
- W3016689222 workType "article" @default.