Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289109828> ?p ?o ?g. }
- W4289109828 endingPage "7702" @default.
- W4289109828 startingPage "7702" @default.
- W4289109828 abstract "Recently, the lexicon method has been proven to be effective for named entity recognition (NER). However, most existing lexicon-based methods cannot fully utilize common-sense knowledge in the knowledge graph. For example, the word embeddings pretrained by Word2vector or Glove lack better contextual semantic information usage. Hence, how to make the best of knowledge for the NER task has become a challenging and hot research topic. We propose a knowledge graph-inspired named-entity recognition (KGNER) featuring a masking and encoding method to incorporate common sense into bidirectional encoder representations from transformers (BERT). The proposed method not only preserves the original sentence semantic information but also takes advantage of the knowledge information in a more reasonable way. Subsequently, we model the temporal dependencies by taking the conditional random field (CRF) as the backend, and improve the overall performance. Experiments on four dominant datasets demonstrate that the KGNER outperforms other lexicon-based models in terms of performance." @default.
- W4289109828 created "2022-08-01" @default.
- W4289109828 creator A5045276244 @default.
- W4289109828 creator A5066706746 @default.
- W4289109828 creator A5071451609 @default.
- W4289109828 creator A5073531557 @default.
- W4289109828 creator A5081731353 @default.
- W4289109828 date "2022-07-30" @default.
- W4289109828 modified "2023-09-26" @default.
- W4289109828 title "KGNER: Improving Chinese Named Entity Recognition by BERT Infused with the Knowledge Graph" @default.
- W4289109828 cites W2250539671 @default.
- W4289109828 cites W2250709962 @default.
- W4289109828 cites W2250807343 @default.
- W4289109828 cites W2251559320 @default.
- W4289109828 cites W2499696929 @default.
- W4289109828 cites W2556343638 @default.
- W4289109828 cites W2759200442 @default.
- W4289109828 cites W2789018230 @default.
- W4289109828 cites W2952595356 @default.
- W4289109828 cites W2998153464 @default.
- W4289109828 cites W2998385486 @default.
- W4289109828 cites W3005852761 @default.
- W4289109828 cites W3079406089 @default.
- W4289109828 cites W3195526979 @default.
- W4289109828 cites W4283395836 @default.
- W4289109828 cites W4285294723 @default.
- W4289109828 doi "https://doi.org/10.3390/app12157702" @default.
- W4289109828 hasPublicationYear "2022" @default.
- W4289109828 type Work @default.
- W4289109828 citedByCount "2" @default.
- W4289109828 countsByYear W42891098282022 @default.
- W4289109828 countsByYear W42891098282023 @default.
- W4289109828 crossrefType "journal-article" @default.
- W4289109828 hasAuthorship W4289109828A5045276244 @default.
- W4289109828 hasAuthorship W4289109828A5066706746 @default.
- W4289109828 hasAuthorship W4289109828A5071451609 @default.
- W4289109828 hasAuthorship W4289109828A5073531557 @default.
- W4289109828 hasAuthorship W4289109828A5081731353 @default.
- W4289109828 hasBestOaLocation W42891098281 @default.
- W4289109828 hasConcept C111919701 @default.
- W4289109828 hasConcept C118505674 @default.
- W4289109828 hasConcept C121332964 @default.
- W4289109828 hasConcept C132525143 @default.
- W4289109828 hasConcept C152565575 @default.
- W4289109828 hasConcept C154945302 @default.
- W4289109828 hasConcept C162324750 @default.
- W4289109828 hasConcept C165801399 @default.
- W4289109828 hasConcept C187736073 @default.
- W4289109828 hasConcept C204321447 @default.
- W4289109828 hasConcept C23123220 @default.
- W4289109828 hasConcept C2777530160 @default.
- W4289109828 hasConcept C2778121359 @default.
- W4289109828 hasConcept C2779135771 @default.
- W4289109828 hasConcept C2780451532 @default.
- W4289109828 hasConcept C2987255567 @default.
- W4289109828 hasConcept C41008148 @default.
- W4289109828 hasConcept C4554734 @default.
- W4289109828 hasConcept C62520636 @default.
- W4289109828 hasConcept C66322947 @default.
- W4289109828 hasConcept C80444323 @default.
- W4289109828 hasConcept C96711827 @default.
- W4289109828 hasConceptScore W4289109828C111919701 @default.
- W4289109828 hasConceptScore W4289109828C118505674 @default.
- W4289109828 hasConceptScore W4289109828C121332964 @default.
- W4289109828 hasConceptScore W4289109828C132525143 @default.
- W4289109828 hasConceptScore W4289109828C152565575 @default.
- W4289109828 hasConceptScore W4289109828C154945302 @default.
- W4289109828 hasConceptScore W4289109828C162324750 @default.
- W4289109828 hasConceptScore W4289109828C165801399 @default.
- W4289109828 hasConceptScore W4289109828C187736073 @default.
- W4289109828 hasConceptScore W4289109828C204321447 @default.
- W4289109828 hasConceptScore W4289109828C23123220 @default.
- W4289109828 hasConceptScore W4289109828C2777530160 @default.
- W4289109828 hasConceptScore W4289109828C2778121359 @default.
- W4289109828 hasConceptScore W4289109828C2779135771 @default.
- W4289109828 hasConceptScore W4289109828C2780451532 @default.
- W4289109828 hasConceptScore W4289109828C2987255567 @default.
- W4289109828 hasConceptScore W4289109828C41008148 @default.
- W4289109828 hasConceptScore W4289109828C4554734 @default.
- W4289109828 hasConceptScore W4289109828C62520636 @default.
- W4289109828 hasConceptScore W4289109828C66322947 @default.
- W4289109828 hasConceptScore W4289109828C80444323 @default.
- W4289109828 hasConceptScore W4289109828C96711827 @default.
- W4289109828 hasIssue "15" @default.
- W4289109828 hasLocation W42891098281 @default.
- W4289109828 hasLocation W42891098282 @default.
- W4289109828 hasOpenAccess W4289109828 @default.
- W4289109828 hasPrimaryLocation W42891098281 @default.
- W4289109828 hasRelatedWork W136407171 @default.
- W4289109828 hasRelatedWork W2045347339 @default.
- W4289109828 hasRelatedWork W2078793151 @default.
- W4289109828 hasRelatedWork W2751906762 @default.
- W4289109828 hasRelatedWork W3003390203 @default.
- W4289109828 hasRelatedWork W3086782256 @default.
- W4289109828 hasRelatedWork W3134928069 @default.
- W4289109828 hasRelatedWork W3180089748 @default.
- W4289109828 hasRelatedWork W3193140313 @default.
- W4289109828 hasRelatedWork W4253099099 @default.