Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213836846> ?p ?o ?g. }
- W3213836846 abstract "Distantly supervised named entity recognition (DS-NER) efficiently reduces labor costs but meanwhile intrinsically suffers from the label noise due to the strong assumption of distant supervision. Typically, the wrongly labeled instances comprise numbers of incomplete and inaccurate annotations, while most prior denoising works are only concerned with one kind of noise and fail to fully explore useful information in the training set. To address this issue, we propose a robust learning paradigm named Self-Collaborative Denoising Learning (SCDL), which jointly trains two teacher-student networks in a mutually-beneficial manner to iteratively perform noisy label refinery. Each network is designed to exploit reliable labels via self denoising, and two networks communicate with each other to explore unreliable annotations by collaborative denoising. Extensive experimental results on five real-world datasets demonstrate that SCDL is superior to state-of-the-art DS-NER denoising methods." @default.
- W3213836846 created "2021-11-22" @default.
- W3213836846 creator A5002716694 @default.
- W3213836846 creator A5045309022 @default.
- W3213836846 creator A5051734211 @default.
- W3213836846 creator A5064217591 @default.
- W3213836846 creator A5080665569 @default.
- W3213836846 creator A5080686378 @default.
- W3213836846 creator A5085842975 @default.
- W3213836846 date "2021-01-01" @default.
- W3213836846 modified "2023-09-25" @default.
- W3213836846 title "Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning" @default.
- W3213836846 cites W1505796919 @default.
- W3213836846 cites W1821462560 @default.
- W3213836846 cites W2004763266 @default.
- W3213836846 cites W2020978905 @default.
- W3213836846 cites W2037603696 @default.
- W3213836846 cites W2048679005 @default.
- W3213836846 cites W2109802279 @default.
- W3213836846 cites W2252278997 @default.
- W3213836846 cites W2296073425 @default.
- W3213836846 cites W2296283641 @default.
- W3213836846 cites W2593560537 @default.
- W3213836846 cites W2734693922 @default.
- W3213836846 cites W2739722817 @default.
- W3213836846 cites W2945214158 @default.
- W3213836846 cites W2953010755 @default.
- W3213836846 cites W2953338005 @default.
- W3213836846 cites W2962902328 @default.
- W3213836846 cites W2963341956 @default.
- W3213836846 cites W2963735582 @default.
- W3213836846 cites W2964121744 @default.
- W3213836846 cites W2965373594 @default.
- W3213836846 cites W2971071849 @default.
- W3213836846 cites W2983651159 @default.
- W3213836846 cites W2986896820 @default.
- W3213836846 cites W2988966271 @default.
- W3213836846 cites W2996108195 @default.
- W3213836846 cites W3101821705 @default.
- W3213836846 cites W3103981637 @default.
- W3213836846 cites W3122921983 @default.
- W3213836846 doi "https://doi.org/10.18653/v1/2021.findings-emnlp.131" @default.
- W3213836846 hasPublicationYear "2021" @default.
- W3213836846 type Work @default.
- W3213836846 sameAs 3213836846 @default.
- W3213836846 citedByCount "1" @default.
- W3213836846 countsByYear W32138368462022 @default.
- W3213836846 crossrefType "proceedings-article" @default.
- W3213836846 hasAuthorship W3213836846A5002716694 @default.
- W3213836846 hasAuthorship W3213836846A5045309022 @default.
- W3213836846 hasAuthorship W3213836846A5051734211 @default.
- W3213836846 hasAuthorship W3213836846A5064217591 @default.
- W3213836846 hasAuthorship W3213836846A5080665569 @default.
- W3213836846 hasAuthorship W3213836846A5080686378 @default.
- W3213836846 hasAuthorship W3213836846A5085842975 @default.
- W3213836846 hasBestOaLocation W32138368461 @default.
- W3213836846 hasConcept C115961682 @default.
- W3213836846 hasConcept C119857082 @default.
- W3213836846 hasConcept C127413603 @default.
- W3213836846 hasConcept C153180895 @default.
- W3213836846 hasConcept C154945302 @default.
- W3213836846 hasConcept C163294075 @default.
- W3213836846 hasConcept C165696696 @default.
- W3213836846 hasConcept C177264268 @default.
- W3213836846 hasConcept C190839683 @default.
- W3213836846 hasConcept C199360897 @default.
- W3213836846 hasConcept C201995342 @default.
- W3213836846 hasConcept C205649164 @default.
- W3213836846 hasConcept C21569690 @default.
- W3213836846 hasConcept C2779135771 @default.
- W3213836846 hasConcept C2780451532 @default.
- W3213836846 hasConcept C38652104 @default.
- W3213836846 hasConcept C41008148 @default.
- W3213836846 hasConcept C557471498 @default.
- W3213836846 hasConcept C58640448 @default.
- W3213836846 hasConcept C99498987 @default.
- W3213836846 hasConceptScore W3213836846C115961682 @default.
- W3213836846 hasConceptScore W3213836846C119857082 @default.
- W3213836846 hasConceptScore W3213836846C127413603 @default.
- W3213836846 hasConceptScore W3213836846C153180895 @default.
- W3213836846 hasConceptScore W3213836846C154945302 @default.
- W3213836846 hasConceptScore W3213836846C163294075 @default.
- W3213836846 hasConceptScore W3213836846C165696696 @default.
- W3213836846 hasConceptScore W3213836846C177264268 @default.
- W3213836846 hasConceptScore W3213836846C190839683 @default.
- W3213836846 hasConceptScore W3213836846C199360897 @default.
- W3213836846 hasConceptScore W3213836846C201995342 @default.
- W3213836846 hasConceptScore W3213836846C205649164 @default.
- W3213836846 hasConceptScore W3213836846C21569690 @default.
- W3213836846 hasConceptScore W3213836846C2779135771 @default.
- W3213836846 hasConceptScore W3213836846C2780451532 @default.
- W3213836846 hasConceptScore W3213836846C38652104 @default.
- W3213836846 hasConceptScore W3213836846C41008148 @default.
- W3213836846 hasConceptScore W3213836846C557471498 @default.
- W3213836846 hasConceptScore W3213836846C58640448 @default.
- W3213836846 hasConceptScore W3213836846C99498987 @default.
- W3213836846 hasLocation W32138368461 @default.
- W3213836846 hasLocation W32138368462 @default.
- W3213836846 hasOpenAccess W3213836846 @default.
- W3213836846 hasPrimaryLocation W32138368461 @default.