Matches in SemOpenAlex for { <https://semopenalex.org/work/W3129023631> ?p ?o ?g. }
- W3129023631 abstract "Clinical Named Entity Recognition (CNER) aims to automatically identity clinical terminologies in Electronic Health Records (EHRs), which is a fundamental and crucial step for clinical research. To train a high-performance model for CNER, it usually requires a large number of EHRs with high-quality labels. However, labeling EHRs, especially Chinese EHRs, is time-consuming and expensive. One effective solution to this issue is active learning, where a model asks labelers to annotate data which is beneficial to model performance improvement. Conventional active learning assumes a single labeler that always replies noiseless answers to queried labels. However, in real settings, multiple labelers provide diverse quality of annotation with varied cost and labelers with low overall annotation quality can still assign correct labels for some specific instances. In this paper, we propose a Cost-Quality Adaptive Active Learning (CQAAL) approach for CNER in Chinese EHRs, which maintains a balance between the annotation quality, labeling cost and the informativeness of selected instances. Specifically, our proposed CQAAL method selects cost-effective instance-labeler pairs to achieve better annotation quality with lower cost in an adaptive manner. Computational results on the CCKS2017 dataset demonstrate the superiority and effectiveness of CQAAL." @default.
- W3129023631 created "2021-02-15" @default.
- W3129023631 creator A5011711527 @default.
- W3129023631 creator A5021549473 @default.
- W3129023631 creator A5071839367 @default.
- W3129023631 date "2020-12-16" @default.
- W3129023631 modified "2023-09-24" @default.
- W3129023631 title "Cost-Quality Adaptive Active Learning for Chinese Clinical Named Entity Recognition" @default.
- W3129023631 cites W1818395637 @default.
- W3129023631 cites W1847088711 @default.
- W3129023631 cites W2064675550 @default.
- W3129023631 cites W2080021732 @default.
- W3129023631 cites W2114361266 @default.
- W3129023631 cites W2117763124 @default.
- W3129023631 cites W2121154891 @default.
- W3129023631 cites W2128518360 @default.
- W3129023631 cites W2134429551 @default.
- W3129023631 cites W2139008537 @default.
- W3129023631 cites W2161816739 @default.
- W3129023631 cites W2171671120 @default.
- W3129023631 cites W2181558882 @default.
- W3129023631 cites W2587019100 @default.
- W3129023631 cites W2740505281 @default.
- W3129023631 cites W2931252866 @default.
- W3129023631 cites W2963341956 @default.
- W3129023631 cites W2963558486 @default.
- W3129023631 cites W2963571188 @default.
- W3129023631 cites W2997654229 @default.
- W3129023631 cites W3003665996 @default.
- W3129023631 cites W3022975064 @default.
- W3129023631 cites W3023618320 @default.
- W3129023631 cites W3034360800 @default.
- W3129023631 cites W3035040493 @default.
- W3129023631 doi "https://doi.org/10.1109/bibm49941.2020.9313302" @default.
- W3129023631 hasPublicationYear "2020" @default.
- W3129023631 type Work @default.
- W3129023631 sameAs 3129023631 @default.
- W3129023631 citedByCount "2" @default.
- W3129023631 countsByYear W31290236312021 @default.
- W3129023631 crossrefType "proceedings-article" @default.
- W3129023631 hasAuthorship W3129023631A5011711527 @default.
- W3129023631 hasAuthorship W3129023631A5021549473 @default.
- W3129023631 hasAuthorship W3129023631A5071839367 @default.
- W3129023631 hasBestOaLocation W31290236312 @default.
- W3129023631 hasConcept C111472728 @default.
- W3129023631 hasConcept C119857082 @default.
- W3129023631 hasConcept C136389625 @default.
- W3129023631 hasConcept C136764020 @default.
- W3129023631 hasConcept C138885662 @default.
- W3129023631 hasConcept C154945302 @default.
- W3129023631 hasConcept C160735492 @default.
- W3129023631 hasConcept C162324750 @default.
- W3129023631 hasConcept C187736073 @default.
- W3129023631 hasConcept C2776321320 @default.
- W3129023631 hasConcept C2779135771 @default.
- W3129023631 hasConcept C2779530757 @default.
- W3129023631 hasConcept C2780451532 @default.
- W3129023631 hasConcept C3019952477 @default.
- W3129023631 hasConcept C41008148 @default.
- W3129023631 hasConcept C50522688 @default.
- W3129023631 hasConcept C50644808 @default.
- W3129023631 hasConcept C62230096 @default.
- W3129023631 hasConcept C77967617 @default.
- W3129023631 hasConceptScore W3129023631C111472728 @default.
- W3129023631 hasConceptScore W3129023631C119857082 @default.
- W3129023631 hasConceptScore W3129023631C136389625 @default.
- W3129023631 hasConceptScore W3129023631C136764020 @default.
- W3129023631 hasConceptScore W3129023631C138885662 @default.
- W3129023631 hasConceptScore W3129023631C154945302 @default.
- W3129023631 hasConceptScore W3129023631C160735492 @default.
- W3129023631 hasConceptScore W3129023631C162324750 @default.
- W3129023631 hasConceptScore W3129023631C187736073 @default.
- W3129023631 hasConceptScore W3129023631C2776321320 @default.
- W3129023631 hasConceptScore W3129023631C2779135771 @default.
- W3129023631 hasConceptScore W3129023631C2779530757 @default.
- W3129023631 hasConceptScore W3129023631C2780451532 @default.
- W3129023631 hasConceptScore W3129023631C3019952477 @default.
- W3129023631 hasConceptScore W3129023631C41008148 @default.
- W3129023631 hasConceptScore W3129023631C50522688 @default.
- W3129023631 hasConceptScore W3129023631C50644808 @default.
- W3129023631 hasConceptScore W3129023631C62230096 @default.
- W3129023631 hasConceptScore W3129023631C77967617 @default.
- W3129023631 hasFunder F4320321001 @default.
- W3129023631 hasLocation W31290236311 @default.
- W3129023631 hasLocation W31290236312 @default.
- W3129023631 hasOpenAccess W3129023631 @default.
- W3129023631 hasPrimaryLocation W31290236311 @default.
- W3129023631 hasRelatedWork W10980763 @default.
- W3129023631 hasRelatedWork W11297145 @default.
- W3129023631 hasRelatedWork W1160799 @default.
- W3129023631 hasRelatedWork W12440339 @default.
- W3129023631 hasRelatedWork W2008886 @default.
- W3129023631 hasRelatedWork W317670 @default.
- W3129023631 hasRelatedWork W3540556 @default.
- W3129023631 hasRelatedWork W4001956 @default.
- W3129023631 hasRelatedWork W5526034 @default.
- W3129023631 hasRelatedWork W8671328 @default.
- W3129023631 isParatext "false" @default.
- W3129023631 isRetracted "false" @default.
- W3129023631 magId "3129023631" @default.