Matches in SemOpenAlex for { <https://semopenalex.org/work/W2997919746> ?p ?o ?g. }
- W2997919746 endingPage "7968" @default.
- W2997919746 startingPage "7961" @default.
- W2997919746 abstract "Most state-of-the-art named entity recognition systems are designed to process each sentence within a document independently. These systems are easy to confuse entity types when the context information in a sentence is not sufficient enough. To utilize the context information within the whole document, most document-level work let neural networks on their own to learn the relation across sentences, which is not intuitive enough for us humans. In this paper, we divide entities to multi-token entities that contain multiple tokens and single-token entities that are composed of a single token. We propose that the context information of multi-token entities should be more reliable in document-level NER for news articles. We design a fusion attention mechanism which not only learns the semantic relevance between occurrences of the same token, but also focuses more on occurrences belonging to multi-tokens entities. To identify multi-token entities, we design an auxiliary task namely ‘Multi-token Entity Classification’ and perform this task simultaneously with document-level NER. This auxiliary task is simplified from NER and doesn't require extra annotation. Experimental results on the CoNLL-2003 dataset and OntoNotesnbm dataset show that our model outperforms state-of-the-art sentence-level and document-level NER methods." @default.
- W2997919746 created "2020-01-10" @default.
- W2997919746 creator A5010558184 @default.
- W2997919746 creator A5018977183 @default.
- W2997919746 creator A5019498452 @default.
- W2997919746 creator A5025631695 @default.
- W2997919746 date "2020-04-03" @default.
- W2997919746 modified "2023-10-01" @default.
- W2997919746 title "Leveraging Multi-Token Entities in Document-Level Named Entity Recognition" @default.
- W2997919746 cites W1940872118 @default.
- W2997919746 cites W1951325712 @default.
- W2997919746 cites W1979960035 @default.
- W2997919746 cites W2004763266 @default.
- W2997919746 cites W2064675550 @default.
- W2997919746 cites W2075635421 @default.
- W2997919746 cites W2088911157 @default.
- W2997919746 cites W2096765155 @default.
- W2997919746 cites W2117813082 @default.
- W2997919746 cites W2133590167 @default.
- W2997919746 cites W2144578941 @default.
- W2997919746 cites W2147880316 @default.
- W2997919746 cites W2158899491 @default.
- W2997919746 cites W2250539671 @default.
- W2997919746 cites W2296283641 @default.
- W2997919746 cites W2574163994 @default.
- W2997919746 cites W2613831280 @default.
- W2997919746 cites W2769387903 @default.
- W2997919746 cites W2798839675 @default.
- W2997919746 cites W2808142148 @default.
- W2997919746 cites W2880875857 @default.
- W2997919746 cites W2884705011 @default.
- W2997919746 cites W2899055307 @default.
- W2997919746 cites W2914278227 @default.
- W2997919746 cites W2921863388 @default.
- W2997919746 cites W2952341153 @default.
- W2997919746 cites W2962739339 @default.
- W2997919746 cites W2962788148 @default.
- W2997919746 cites W2962902328 @default.
- W2997919746 cites W2962906565 @default.
- W2997919746 cites W2963140597 @default.
- W2997919746 cites W2963341956 @default.
- W2997919746 cites W2963625095 @default.
- W2997919746 cites W2963641259 @default.
- W2997919746 cites W2963917673 @default.
- W2997919746 cites W2964308564 @default.
- W2997919746 doi "https://doi.org/10.1609/aaai.v34i05.6304" @default.
- W2997919746 hasPublicationYear "2020" @default.
- W2997919746 type Work @default.
- W2997919746 sameAs 2997919746 @default.
- W2997919746 citedByCount "20" @default.
- W2997919746 countsByYear W29979197462020 @default.
- W2997919746 countsByYear W29979197462021 @default.
- W2997919746 countsByYear W29979197462022 @default.
- W2997919746 countsByYear W29979197462023 @default.
- W2997919746 crossrefType "journal-article" @default.
- W2997919746 hasAuthorship W2997919746A5010558184 @default.
- W2997919746 hasAuthorship W2997919746A5018977183 @default.
- W2997919746 hasAuthorship W2997919746A5019498452 @default.
- W2997919746 hasAuthorship W2997919746A5025631695 @default.
- W2997919746 hasBestOaLocation W29979197461 @default.
- W2997919746 hasConcept C151730666 @default.
- W2997919746 hasConcept C154945302 @default.
- W2997919746 hasConcept C158154518 @default.
- W2997919746 hasConcept C162324750 @default.
- W2997919746 hasConcept C17744445 @default.
- W2997919746 hasConcept C187736073 @default.
- W2997919746 hasConcept C199360897 @default.
- W2997919746 hasConcept C199539241 @default.
- W2997919746 hasConcept C204321447 @default.
- W2997919746 hasConcept C23123220 @default.
- W2997919746 hasConcept C2776321320 @default.
- W2997919746 hasConcept C2777530160 @default.
- W2997919746 hasConcept C2779135771 @default.
- W2997919746 hasConcept C2779343474 @default.
- W2997919746 hasConcept C2780451532 @default.
- W2997919746 hasConcept C38652104 @default.
- W2997919746 hasConcept C41008148 @default.
- W2997919746 hasConcept C48145219 @default.
- W2997919746 hasConcept C86803240 @default.
- W2997919746 hasConcept C98045186 @default.
- W2997919746 hasConceptScore W2997919746C151730666 @default.
- W2997919746 hasConceptScore W2997919746C154945302 @default.
- W2997919746 hasConceptScore W2997919746C158154518 @default.
- W2997919746 hasConceptScore W2997919746C162324750 @default.
- W2997919746 hasConceptScore W2997919746C17744445 @default.
- W2997919746 hasConceptScore W2997919746C187736073 @default.
- W2997919746 hasConceptScore W2997919746C199360897 @default.
- W2997919746 hasConceptScore W2997919746C199539241 @default.
- W2997919746 hasConceptScore W2997919746C204321447 @default.
- W2997919746 hasConceptScore W2997919746C23123220 @default.
- W2997919746 hasConceptScore W2997919746C2776321320 @default.
- W2997919746 hasConceptScore W2997919746C2777530160 @default.
- W2997919746 hasConceptScore W2997919746C2779135771 @default.
- W2997919746 hasConceptScore W2997919746C2779343474 @default.
- W2997919746 hasConceptScore W2997919746C2780451532 @default.
- W2997919746 hasConceptScore W2997919746C38652104 @default.
- W2997919746 hasConceptScore W2997919746C41008148 @default.
- W2997919746 hasConceptScore W2997919746C48145219 @default.