Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385571570> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4385571570 abstract "We compare three simple and popular approaches for NER: 1) SEQ (sequence labeling with a linear token classifier) 2) SeqCRF (sequence labeling with Conditional Random Fields), and 3) SpanPred (span prediction with boundary token embeddings). We compare the approaches on 4 biomedical NER tasks: GENIA, NCBI-Disease, LivingNER (Spanish), and SocialDisNER (Spanish). The SpanPred model demonstrates state-of-the-art performance on LivingNER and SocialDisNER, improving F1 by 1.3 and 0.6 F1 respectively. The SeqCRF model also demonstrates state-of-the-art performance on LivingNER and SocialDisNER, improving F1 by 0.2 F1 and 0.7 respectively. The SEQ model is competitive with the state-of-the-art on LivingNER dataset. We explore some simple ways of combining the three approaches. We find that majority voting consistently gives high precision and high F1 across all 4 datasets.Lastly, we implement a system that learns to combine SEQ’s and SpanPred’s predictions, generating systems that give high recall and high F1 across all 4 datasets. On the GENIA dataset, we find that our learned combiner system significantly boosts F1(+1.2) and recall(+2.1) over the systems being combined." @default.
- W4385571570 created "2023-08-05" @default.
- W4385571570 creator A5003653341 @default.
- W4385571570 creator A5008304272 @default.
- W4385571570 creator A5092061448 @default.
- W4385571570 date "2023-01-01" @default.
- W4385571570 modified "2023-09-27" @default.
- W4385571570 title "Comparing and combining some popular NER approaches on Biomedical tasks" @default.
- W4385571570 doi "https://doi.org/10.18653/v1/2023.bionlp-1.24" @default.
- W4385571570 hasPublicationYear "2023" @default.
- W4385571570 type Work @default.
- W4385571570 citedByCount "0" @default.
- W4385571570 crossrefType "proceedings-article" @default.
- W4385571570 hasAuthorship W4385571570A5003653341 @default.
- W4385571570 hasAuthorship W4385571570A5008304272 @default.
- W4385571570 hasAuthorship W4385571570A5092061448 @default.
- W4385571570 hasBestOaLocation W43855715701 @default.
- W4385571570 hasConcept C111472728 @default.
- W4385571570 hasConcept C119857082 @default.
- W4385571570 hasConcept C138885662 @default.
- W4385571570 hasConcept C148524875 @default.
- W4385571570 hasConcept C152565575 @default.
- W4385571570 hasConcept C154945302 @default.
- W4385571570 hasConcept C162324750 @default.
- W4385571570 hasConcept C187736073 @default.
- W4385571570 hasConcept C2778112365 @default.
- W4385571570 hasConcept C2779135771 @default.
- W4385571570 hasConcept C2780451532 @default.
- W4385571570 hasConcept C2780586882 @default.
- W4385571570 hasConcept C35639132 @default.
- W4385571570 hasConcept C38652104 @default.
- W4385571570 hasConcept C41008148 @default.
- W4385571570 hasConcept C48145219 @default.
- W4385571570 hasConcept C54355233 @default.
- W4385571570 hasConcept C86803240 @default.
- W4385571570 hasConcept C95623464 @default.
- W4385571570 hasConceptScore W4385571570C111472728 @default.
- W4385571570 hasConceptScore W4385571570C119857082 @default.
- W4385571570 hasConceptScore W4385571570C138885662 @default.
- W4385571570 hasConceptScore W4385571570C148524875 @default.
- W4385571570 hasConceptScore W4385571570C152565575 @default.
- W4385571570 hasConceptScore W4385571570C154945302 @default.
- W4385571570 hasConceptScore W4385571570C162324750 @default.
- W4385571570 hasConceptScore W4385571570C187736073 @default.
- W4385571570 hasConceptScore W4385571570C2778112365 @default.
- W4385571570 hasConceptScore W4385571570C2779135771 @default.
- W4385571570 hasConceptScore W4385571570C2780451532 @default.
- W4385571570 hasConceptScore W4385571570C2780586882 @default.
- W4385571570 hasConceptScore W4385571570C35639132 @default.
- W4385571570 hasConceptScore W4385571570C38652104 @default.
- W4385571570 hasConceptScore W4385571570C41008148 @default.
- W4385571570 hasConceptScore W4385571570C48145219 @default.
- W4385571570 hasConceptScore W4385571570C54355233 @default.
- W4385571570 hasConceptScore W4385571570C86803240 @default.
- W4385571570 hasConceptScore W4385571570C95623464 @default.
- W4385571570 hasLocation W43855715701 @default.
- W4385571570 hasOpenAccess W4385571570 @default.
- W4385571570 hasPrimaryLocation W43855715701 @default.
- W4385571570 hasRelatedWork W1494482382 @default.
- W4385571570 hasRelatedWork W1989517911 @default.
- W4385571570 hasRelatedWork W2110399939 @default.
- W4385571570 hasRelatedWork W2589080577 @default.
- W4385571570 hasRelatedWork W2926424521 @default.
- W4385571570 hasRelatedWork W2943381814 @default.
- W4385571570 hasRelatedWork W2947903144 @default.
- W4385571570 hasRelatedWork W3082457427 @default.
- W4385571570 hasRelatedWork W4225452288 @default.
- W4385571570 hasRelatedWork W4297192989 @default.
- W4385571570 isParatext "false" @default.
- W4385571570 isRetracted "false" @default.
- W4385571570 workType "article" @default.