FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3104774463> ?p ?o ?g. }

• W3104774463 endingPage "4256" @default.
• W3104774463 startingPage "4245" @default.
• W3104774463 abstract "Few-shot learning under the <inline-formula><tex-math notation=LaTeX>$N$</tex-math></inline-formula> -way <inline-formula><tex-math notation=LaTeX>$K$</tex-math></inline-formula> -shot setting (i.e., <inline-formula><tex-math notation=LaTeX>$K$</tex-math></inline-formula> annotated samples for each of <inline-formula><tex-math notation=LaTeX>$N$</tex-math></inline-formula> classes) has been widely studied in relation extraction (e.g., FewRel) and image classification (e.g., Mini-ImageNet). Named entity recognition (NER) is typically framed as a sequence labeling problem where the entity classes are inherently entangled together because the entity number and classes in a sentence are not known in advance, leaving the <inline-formula><tex-math notation=LaTeX>$N$</tex-math></inline-formula> -way <inline-formula><tex-math notation=LaTeX>$K$</tex-math></inline-formula> -shot NER problem so far unexplored. In this paper, we first formally define a more suitable <inline-formula><tex-math notation=LaTeX>$N$</tex-math></inline-formula> -way <inline-formula><tex-math notation=LaTeX>$K$</tex-math></inline-formula> -shot setting for NER. Then we propose <small>FewNER</small> , a novel meta-learning approach for few-shot NER. <small>FewNER</small> separates the entire network into a task-independent part and a task-specific part. During training in <small>FewNER</small> , the task-independent part is meta-learned across multiple tasks and the task-specific part is learned for each individual task in a low-dimensional space. At test time, <small>FewNER</small> keeps the task-independent part fixed and adapts to a new task via gradient descent by updating only the task-specific part, resulting in it being less prone to overfitting and more computationally efficient. Compared with pre-trained language models (e.g., BERT and ELMo) which obtain the transferability in an implicit manner (i.e., relying on large-scale corpora), <small>FewNER</small> explicitly optimizes the capability of “learning to adapt quickly” through meta-learning. The results demonstrate that <small>FewNER</small> achieves state-of-the-art performance against nine baseline methods by significant margins on three adaptation experiments (i.e., intra-domain cross-type, cross-domain intra-type and cross-domain cross-type)." @default.
• W3104774463 created "2020-11-23" @default.
• W3104774463 creator A5024945225 @default.
• W3104774463 creator A5068192328 @default.
• W3104774463 creator A5076988964 @default.
• W3104774463 creator A5086115549 @default.
• W3104774463 date "2022-09-01" @default.
• W3104774463 modified "2023-10-06" @default.
• W3104774463 title "Few-Shot Named Entity Recognition via Meta-Learning" @default.
• W3104774463 cites W2020278455 @default.
• W3104774463 cites W2028122758 @default.
• W3104774463 cites W2098700435 @default.
• W3104774463 cites W2115633168 @default.
• W3104774463 cites W2123556395 @default.
• W3104774463 cites W2148540243 @default.
• W3104774463 cites W2165698076 @default.
• W3104774463 cites W2296283641 @default.
• W3104774463 cites W2337748376 @default.
• W3104774463 cites W2474198877 @default.
• W3104774463 cites W2757016069 @default.
• W3104774463 cites W2758765981 @default.
• W3104774463 cites W2760103357 @default.
• W3104774463 cites W2798778171 @default.
• W3104774463 cites W2804221886 @default.
• W3104774463 cites W2807938752 @default.
• W3104774463 cites W2888541716 @default.
• W3104774463 cites W2890494294 @default.
• W3104774463 cites W2904415434 @default.
• W3104774463 cites W2915716523 @default.
• W3104774463 cites W2949176808 @default.
• W3104774463 cites W2949759300 @default.
• W3104774463 cites W2951221758 @default.
• W3104774463 cites W2951820126 @default.
• W3104774463 cites W2951980657 @default.
• W3104774463 cites W2953111196 @default.
• W3104774463 cites W2962739339 @default.
• W3104774463 cites W2962902328 @default.
• W3104774463 cites W2963140597 @default.
• W3104774463 cites W2963339489 @default.
• W3104774463 cites W2963571583 @default.
• W3104774463 cites W2963777632 @default.
• W3104774463 cites W2963845150 @default.
• W3104774463 cites W2963866663 @default.
• W3104774463 cites W2965435509 @default.
• W3104774463 cites W2997124358 @default.
• W3104774463 cites W3011594683 @default.
• W3104774463 cites W99485931 @default.
• W3104774463 doi "https://doi.org/10.1109/tkde.2020.3038670" @default.
• W3104774463 hasPublicationYear "2022" @default.
• W3104774463 type Work @default.
• W3104774463 sameAs 3104774463 @default.
• W3104774463 citedByCount "61" @default.
• W3104774463 countsByYear W31047744632020 @default.
• W3104774463 countsByYear W31047744632021 @default.
• W3104774463 countsByYear W31047744632022 @default.
• W3104774463 countsByYear W31047744632023 @default.
• W3104774463 crossrefType "journal-article" @default.
• W3104774463 hasAuthorship W3104774463A5024945225 @default.
• W3104774463 hasAuthorship W3104774463A5068192328 @default.
• W3104774463 hasAuthorship W3104774463A5076988964 @default.
• W3104774463 hasAuthorship W3104774463A5086115549 @default.
• W3104774463 hasConcept C118615104 @default.
• W3104774463 hasConcept C154945302 @default.
• W3104774463 hasConcept C162324750 @default.
• W3104774463 hasConcept C178790620 @default.
• W3104774463 hasConcept C185592680 @default.
• W3104774463 hasConcept C187736073 @default.
• W3104774463 hasConcept C24457124 @default.
• W3104774463 hasConcept C2777530160 @default.
• W3104774463 hasConcept C2778344882 @default.
• W3104774463 hasConcept C2780451532 @default.
• W3104774463 hasConcept C33923547 @default.
• W3104774463 hasConcept C41008148 @default.
• W3104774463 hasConcept C45357846 @default.
• W3104774463 hasConcept C94375191 @default.
• W3104774463 hasConceptScore W3104774463C118615104 @default.
• W3104774463 hasConceptScore W3104774463C154945302 @default.
• W3104774463 hasConceptScore W3104774463C162324750 @default.
• W3104774463 hasConceptScore W3104774463C178790620 @default.
• W3104774463 hasConceptScore W3104774463C185592680 @default.
• W3104774463 hasConceptScore W3104774463C187736073 @default.
• W3104774463 hasConceptScore W3104774463C24457124 @default.
• W3104774463 hasConceptScore W3104774463C2777530160 @default.
• W3104774463 hasConceptScore W3104774463C2778344882 @default.
• W3104774463 hasConceptScore W3104774463C2780451532 @default.
• W3104774463 hasConceptScore W3104774463C33923547 @default.
• W3104774463 hasConceptScore W3104774463C41008148 @default.
• W3104774463 hasConceptScore W3104774463C45357846 @default.
• W3104774463 hasConceptScore W3104774463C94375191 @default.
• W3104774463 hasIssue "9" @default.
• W3104774463 hasLocation W31047744631 @default.
• W3104774463 hasOpenAccess W3104774463 @default.
• W3104774463 hasPrimaryLocation W31047744631 @default.
• W3104774463 hasRelatedWork W1968256718 @default.
• W3104774463 hasRelatedWork W2035950535 @default.
• W3104774463 hasRelatedWork W2081647779 @default.
• W3104774463 hasRelatedWork W2088953969 @default.
• W3104774463 hasRelatedWork W2301135490 @default.

• next