Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309567576> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4309567576 endingPage "110125" @default.
- W4309567576 startingPage "110125" @default.
- W4309567576 abstract "Attention-based models have been widely used in aspect-level sentiment analysis owing to their contextual semantic-alignment capabilities. However, these models lack a mechanism that can incorporate syntactic tendencies. Thus, attention-based neural networks are less accurate when dealing with complex syntactic relationships and long-span syntactically dependent utterances. To solve this problem, a neural network model combining a conditional random field and a graph convolutional network is proposed. The model uses a conditional random field chain to extract the opinion span of an aspect-specific word, integrates the contextual information within the opinion span to the global nodes through a multilayer graph convolutional network using the improved position decay function, and predicts the aspect-specific sentiment polarity labels by computing the vector expressions of the global nodes. This study addresses the problem of fluctuations in model accuracy when multiple aspect words exist in an utterance by introducing global nodes into a graph convolutional network. The proposed model performed well in the experiments on all four datasets tested." @default.
- W4309567576 created "2022-11-28" @default.
- W4309567576 creator A5012873397 @default.
- W4309567576 creator A5017385106 @default.
- W4309567576 creator A5024708084 @default.
- W4309567576 creator A5042597849 @default.
- W4309567576 creator A5062798207 @default.
- W4309567576 creator A5079691564 @default.
- W4309567576 date "2023-01-01" @default.
- W4309567576 modified "2023-10-04" @default.
- W4309567576 title "CRF-GCN: An effective syntactic dependency model for aspect-level sentiment analysis" @default.
- W4309567576 cites W2050106721 @default.
- W4309567576 cites W2250539671 @default.
- W4309567576 cites W2251294039 @default.
- W4309567576 cites W2252057809 @default.
- W4309567576 cites W2306941105 @default.
- W4309567576 cites W2465978385 @default.
- W4309567576 cites W2562607067 @default.
- W4309567576 cites W2757541972 @default.
- W4309567576 cites W2788610610 @default.
- W4309567576 cites W2949161734 @default.
- W4309567576 cites W2962692632 @default.
- W4309567576 cites W2963168371 @default.
- W4309567576 cites W2963240575 @default.
- W4309567576 cites W2964164368 @default.
- W4309567576 cites W2964199361 @default.
- W4309567576 cites W2970183009 @default.
- W4309567576 cites W2970583420 @default.
- W4309567576 cites W2970748008 @default.
- W4309567576 cites W2971220558 @default.
- W4309567576 cites W3035529900 @default.
- W4309567576 cites W3100451998 @default.
- W4309567576 cites W3100456868 @default.
- W4309567576 cites W3210828003 @default.
- W4309567576 cites W4212852237 @default.
- W4309567576 cites W4285306086 @default.
- W4309567576 cites W4287854714 @default.
- W4309567576 cites W4293704567 @default.
- W4309567576 doi "https://doi.org/10.1016/j.knosys.2022.110125" @default.
- W4309567576 hasPublicationYear "2023" @default.
- W4309567576 type Work @default.
- W4309567576 citedByCount "3" @default.
- W4309567576 countsByYear W43095675762023 @default.
- W4309567576 crossrefType "journal-article" @default.
- W4309567576 hasAuthorship W4309567576A5012873397 @default.
- W4309567576 hasAuthorship W4309567576A5017385106 @default.
- W4309567576 hasAuthorship W4309567576A5024708084 @default.
- W4309567576 hasAuthorship W4309567576A5042597849 @default.
- W4309567576 hasAuthorship W4309567576A5062798207 @default.
- W4309567576 hasAuthorship W4309567576A5079691564 @default.
- W4309567576 hasConcept C132525143 @default.
- W4309567576 hasConcept C152565575 @default.
- W4309567576 hasConcept C154945302 @default.
- W4309567576 hasConcept C19768560 @default.
- W4309567576 hasConcept C204321447 @default.
- W4309567576 hasConcept C2775852435 @default.
- W4309567576 hasConcept C41008148 @default.
- W4309567576 hasConcept C66402592 @default.
- W4309567576 hasConcept C80444323 @default.
- W4309567576 hasConcept C81363708 @default.
- W4309567576 hasConceptScore W4309567576C132525143 @default.
- W4309567576 hasConceptScore W4309567576C152565575 @default.
- W4309567576 hasConceptScore W4309567576C154945302 @default.
- W4309567576 hasConceptScore W4309567576C19768560 @default.
- W4309567576 hasConceptScore W4309567576C204321447 @default.
- W4309567576 hasConceptScore W4309567576C2775852435 @default.
- W4309567576 hasConceptScore W4309567576C41008148 @default.
- W4309567576 hasConceptScore W4309567576C66402592 @default.
- W4309567576 hasConceptScore W4309567576C80444323 @default.
- W4309567576 hasConceptScore W4309567576C81363708 @default.
- W4309567576 hasLocation W43095675761 @default.
- W4309567576 hasOpenAccess W4309567576 @default.
- W4309567576 hasPrimaryLocation W43095675761 @default.
- W4309567576 hasRelatedWork W1803059841 @default.
- W4309567576 hasRelatedWork W1992228221 @default.
- W4309567576 hasRelatedWork W2005138141 @default.
- W4309567576 hasRelatedWork W2117176186 @default.
- W4309567576 hasRelatedWork W2732626551 @default.
- W4309567576 hasRelatedWork W2902798395 @default.
- W4309567576 hasRelatedWork W2972981634 @default.
- W4309567576 hasRelatedWork W3168129742 @default.
- W4309567576 hasRelatedWork W4200472398 @default.
- W4309567576 hasRelatedWork W4310608751 @default.
- W4309567576 hasVolume "260" @default.
- W4309567576 isParatext "false" @default.
- W4309567576 isRetracted "false" @default.
- W4309567576 workType "article" @default.