Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225103632> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4225103632 abstract "Nested named entity recognition (nested NER) is a fundamental task in natural language processing. Various span-based methods have been proposed to detect nested entities with span representations. However, span-based methods do not consider the relationship between a span and other entities or phrases, which is helpful in the NER task. Besides, span-based methods have trouble predicting long entities due to limited span enumeration length. To mitigate these issues, we present the Propose-and-Refine Network (PnRNet), a two-stage set prediction network for nested NER. In the propose stage, we use a span-based predictor to generate some coarse entity predictions as entity proposals. In the refine stage, proposals interact with each other, and richer contextual information is incorporated into the proposal representations. The refined proposal representations are used to re-predict entity boundaries and classes. In this way, errors in coarse proposals can be eliminated, and the boundary prediction is no longer constrained by the span enumeration length limitation. Additionally, we build multi-scale sentence representations, which better model the hierarchical structure of sentences and provide richer contextual information than token-level representations. Experiments show that PnRNet achieves state-of-the-art performance on four nested NER datasets and one flat NER dataset." @default.
- W4225103632 created "2022-04-30" @default.
- W4225103632 creator A5004068482 @default.
- W4225103632 creator A5004615610 @default.
- W4225103632 creator A5026310569 @default.
- W4225103632 creator A5060694956 @default.
- W4225103632 date "2022-07-01" @default.
- W4225103632 modified "2023-10-15" @default.
- W4225103632 title "Propose-and-Refine: A Two-Stage Set Prediction Network for Nested Named Entity Recognition" @default.
- W4225103632 doi "https://doi.org/10.24963/ijcai.2022/610" @default.
- W4225103632 hasPublicationYear "2022" @default.
- W4225103632 type Work @default.
- W4225103632 citedByCount "0" @default.
- W4225103632 crossrefType "proceedings-article" @default.
- W4225103632 hasAuthorship W4225103632A5004068482 @default.
- W4225103632 hasAuthorship W4225103632A5004615610 @default.
- W4225103632 hasAuthorship W4225103632A5026310569 @default.
- W4225103632 hasAuthorship W4225103632A5060694956 @default.
- W4225103632 hasBestOaLocation W42251036321 @default.
- W4225103632 hasConcept C127413603 @default.
- W4225103632 hasConcept C134306372 @default.
- W4225103632 hasConcept C147176958 @default.
- W4225103632 hasConcept C154945302 @default.
- W4225103632 hasConcept C162324750 @default.
- W4225103632 hasConcept C177264268 @default.
- W4225103632 hasConcept C187736073 @default.
- W4225103632 hasConcept C19768560 @default.
- W4225103632 hasConcept C199360897 @default.
- W4225103632 hasConcept C204321447 @default.
- W4225103632 hasConcept C2777530160 @default.
- W4225103632 hasConcept C2778753569 @default.
- W4225103632 hasConcept C2779135771 @default.
- W4225103632 hasConcept C2780451532 @default.
- W4225103632 hasConcept C33923547 @default.
- W4225103632 hasConcept C38652104 @default.
- W4225103632 hasConcept C41008148 @default.
- W4225103632 hasConcept C48145219 @default.
- W4225103632 hasConcept C62354387 @default.
- W4225103632 hasConceptScore W4225103632C127413603 @default.
- W4225103632 hasConceptScore W4225103632C134306372 @default.
- W4225103632 hasConceptScore W4225103632C147176958 @default.
- W4225103632 hasConceptScore W4225103632C154945302 @default.
- W4225103632 hasConceptScore W4225103632C162324750 @default.
- W4225103632 hasConceptScore W4225103632C177264268 @default.
- W4225103632 hasConceptScore W4225103632C187736073 @default.
- W4225103632 hasConceptScore W4225103632C19768560 @default.
- W4225103632 hasConceptScore W4225103632C199360897 @default.
- W4225103632 hasConceptScore W4225103632C204321447 @default.
- W4225103632 hasConceptScore W4225103632C2777530160 @default.
- W4225103632 hasConceptScore W4225103632C2778753569 @default.
- W4225103632 hasConceptScore W4225103632C2779135771 @default.
- W4225103632 hasConceptScore W4225103632C2780451532 @default.
- W4225103632 hasConceptScore W4225103632C33923547 @default.
- W4225103632 hasConceptScore W4225103632C38652104 @default.
- W4225103632 hasConceptScore W4225103632C41008148 @default.
- W4225103632 hasConceptScore W4225103632C48145219 @default.
- W4225103632 hasConceptScore W4225103632C62354387 @default.
- W4225103632 hasLocation W42251036321 @default.
- W4225103632 hasLocation W42251036322 @default.
- W4225103632 hasOpenAccess W4225103632 @default.
- W4225103632 hasPrimaryLocation W42251036321 @default.
- W4225103632 hasRelatedWork W147166030 @default.
- W4225103632 hasRelatedWork W159132833 @default.
- W4225103632 hasRelatedWork W1978971213 @default.
- W4225103632 hasRelatedWork W2081647779 @default.
- W4225103632 hasRelatedWork W2155524666 @default.
- W4225103632 hasRelatedWork W2810280135 @default.
- W4225103632 hasRelatedWork W3107474891 @default.
- W4225103632 hasRelatedWork W3116646283 @default.
- W4225103632 hasRelatedWork W4210250015 @default.
- W4225103632 hasRelatedWork W4297192989 @default.
- W4225103632 isParatext "false" @default.
- W4225103632 isRetracted "false" @default.
- W4225103632 workType "article" @default.