Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308691330> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4308691330 abstract "Script event prediction usually refers to giving a sequence of contextual events and then selecting the most likely subsequent event from multiple candidate events. Usually, script event prediction methods are based on event pairs or event chain methods to build prediction models, but these methods can not fully capture the complex relationship between context events and candidate events. Aiming at the two difficulties of how to fully mine the meaning of events in text data to accurately represent events and how to make full use of the potential information between event nodes in narrative event graph to improve the accuracy of prediction tasks, this paper proposes a script event prediction model Bert-SatGNN, which combines Bert pre-training model, structural self-attention mechanism and narrative event graph. Our model introduces Bert pre-training mechanism into script event prediction for the first time so that it can more accurately represent the event nodes input into the prediction model. And use the multi-head structure self-attention module to learn the structural information of the event nodes in the narrative event graph, so as to capture the potential information of evolutionary events with causal logic, and finally combine the structural information and time series information to predict the final events. In this paper, experiments are carried out on the widely used New York Times data set, and the experimental results show that our models are better than the most advanced methods." @default.
- W4308691330 created "2022-11-14" @default.
- W4308691330 creator A5004515575 @default.
- W4308691330 creator A5014189055 @default.
- W4308691330 creator A5054976327 @default.
- W4308691330 date "2022-10-03" @default.
- W4308691330 modified "2023-10-16" @default.
- W4308691330 title "Script event prediction method based on self-attention mechanism and graph representation learning" @default.
- W4308691330 cites W2157331557 @default.
- W4308691330 cites W2257051837 @default.
- W4308691330 cites W2758362814 @default.
- W4308691330 cites W2964080504 @default.
- W4308691330 cites W3142077573 @default.
- W4308691330 cites W3210448484 @default.
- W4308691330 cites W4206270770 @default.
- W4308691330 cites W4293547730 @default.
- W4308691330 doi "https://doi.org/10.1109/iaeac54830.2022.9929851" @default.
- W4308691330 hasPublicationYear "2022" @default.
- W4308691330 type Work @default.
- W4308691330 citedByCount "0" @default.
- W4308691330 crossrefType "proceedings-article" @default.
- W4308691330 hasAuthorship W4308691330A5004515575 @default.
- W4308691330 hasAuthorship W4308691330A5014189055 @default.
- W4308691330 hasAuthorship W4308691330A5054976327 @default.
- W4308691330 hasConcept C119857082 @default.
- W4308691330 hasConcept C121332964 @default.
- W4308691330 hasConcept C124101348 @default.
- W4308691330 hasConcept C132525143 @default.
- W4308691330 hasConcept C151730666 @default.
- W4308691330 hasConcept C154945302 @default.
- W4308691330 hasConcept C204321447 @default.
- W4308691330 hasConcept C2779343474 @default.
- W4308691330 hasConcept C2779662365 @default.
- W4308691330 hasConcept C41008148 @default.
- W4308691330 hasConcept C62520636 @default.
- W4308691330 hasConcept C80444323 @default.
- W4308691330 hasConcept C86803240 @default.
- W4308691330 hasConceptScore W4308691330C119857082 @default.
- W4308691330 hasConceptScore W4308691330C121332964 @default.
- W4308691330 hasConceptScore W4308691330C124101348 @default.
- W4308691330 hasConceptScore W4308691330C132525143 @default.
- W4308691330 hasConceptScore W4308691330C151730666 @default.
- W4308691330 hasConceptScore W4308691330C154945302 @default.
- W4308691330 hasConceptScore W4308691330C204321447 @default.
- W4308691330 hasConceptScore W4308691330C2779343474 @default.
- W4308691330 hasConceptScore W4308691330C2779662365 @default.
- W4308691330 hasConceptScore W4308691330C41008148 @default.
- W4308691330 hasConceptScore W4308691330C62520636 @default.
- W4308691330 hasConceptScore W4308691330C80444323 @default.
- W4308691330 hasConceptScore W4308691330C86803240 @default.
- W4308691330 hasFunder F4320335777 @default.
- W4308691330 hasFunder F4320335787 @default.
- W4308691330 hasLocation W43086913301 @default.
- W4308691330 hasOpenAccess W4308691330 @default.
- W4308691330 hasPrimaryLocation W43086913301 @default.
- W4308691330 hasRelatedWork W2611614995 @default.
- W4308691330 hasRelatedWork W2961085424 @default.
- W4308691330 hasRelatedWork W3046775127 @default.
- W4308691330 hasRelatedWork W3107474891 @default.
- W4308691330 hasRelatedWork W3170094116 @default.
- W4308691330 hasRelatedWork W4285260836 @default.
- W4308691330 hasRelatedWork W4286629047 @default.
- W4308691330 hasRelatedWork W4306321456 @default.
- W4308691330 hasRelatedWork W4306674287 @default.
- W4308691330 hasRelatedWork W4224009465 @default.
- W4308691330 isParatext "false" @default.
- W4308691330 isRetracted "false" @default.
- W4308691330 workType "article" @default.