Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385647457> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4385647457 abstract "Abstract Motivation Few-shot learning that can effectively perform named entity recognition in low-resource scenarios has raised growing attention, but it has not been widely studied yet in the biomedical field. In contrast to high-resource domains, biomedical named entity recognition (BioNER) often encounters limited human-labeled data in real-world scenarios, leading to poor generalization performance when training only a few labeled instances. Recent approaches either leverage cross-domain high-resource data or fine-tune the pre-trained masked language model using limited labeled samples to generate new synthetic data, which is easily stuck in domain shift problems or yields low-quality synthetic data. Therefore, in this article, we study a more realistic scenario, i.e. few-shot learning for BioNER. Results Leveraging the domain knowledge graph, we propose knowledge-guided instance generation for few-shot BioNER, which generates diverse and novel entities based on similar semantic relations of neighbor nodes. In addition, by introducing question prompt, we cast BioNER as question-answering task and propose prompt contrastive learning to improve the robustness of the model by measuring the mutual information between query–answer pairs. Extensive experiments conducted on various few-shot settings show that the proposed framework achieves superior performance. Particularly, in a low-resource scenario with only 20 samples, our approach substantially outperforms recent state-of-the-art models on four benchmark datasets, achieving an average improvement of up to 7.1% F1. Availability and implementation Our source code and data are available at https://github.com/cpmss521/KGPC." @default.
- W4385647457 created "2023-08-09" @default.
- W4385647457 creator A5008961920 @default.
- W4385647457 creator A5017835678 @default.
- W4385647457 creator A5023931221 @default.
- W4385647457 creator A5032764121 @default.
- W4385647457 creator A5051597671 @default.
- W4385647457 date "2023-08-01" @default.
- W4385647457 modified "2023-09-27" @default.
- W4385647457 title "Few-shot biomedical named entity recognition via knowledge-guided instance generation and prompt contrastive learning" @default.
- W4385647457 cites W1550258693 @default.
- W4385647457 cites W2159583324 @default.
- W4385647457 cites W2169099542 @default.
- W4385647457 cites W2911489562 @default.
- W4385647457 cites W3156000544 @default.
- W4385647457 cites W4229050495 @default.
- W4385647457 doi "https://doi.org/10.1093/bioinformatics/btad496" @default.
- W4385647457 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37549065" @default.
- W4385647457 hasPublicationYear "2023" @default.
- W4385647457 type Work @default.
- W4385647457 citedByCount "0" @default.
- W4385647457 crossrefType "journal-article" @default.
- W4385647457 hasAuthorship W4385647457A5008961920 @default.
- W4385647457 hasAuthorship W4385647457A5017835678 @default.
- W4385647457 hasAuthorship W4385647457A5023931221 @default.
- W4385647457 hasAuthorship W4385647457A5032764121 @default.
- W4385647457 hasAuthorship W4385647457A5051597671 @default.
- W4385647457 hasBestOaLocation W43856474571 @default.
- W4385647457 hasConcept C104317684 @default.
- W4385647457 hasConcept C111919701 @default.
- W4385647457 hasConcept C119857082 @default.
- W4385647457 hasConcept C13280743 @default.
- W4385647457 hasConcept C134306372 @default.
- W4385647457 hasConcept C153083717 @default.
- W4385647457 hasConcept C154945302 @default.
- W4385647457 hasConcept C162324750 @default.
- W4385647457 hasConcept C177148314 @default.
- W4385647457 hasConcept C185592680 @default.
- W4385647457 hasConcept C185798385 @default.
- W4385647457 hasConcept C187736073 @default.
- W4385647457 hasConcept C204321447 @default.
- W4385647457 hasConcept C205649164 @default.
- W4385647457 hasConcept C2776145971 @default.
- W4385647457 hasConcept C2776321320 @default.
- W4385647457 hasConcept C2779135771 @default.
- W4385647457 hasConcept C2780451532 @default.
- W4385647457 hasConcept C33923547 @default.
- W4385647457 hasConcept C41008148 @default.
- W4385647457 hasConcept C43126263 @default.
- W4385647457 hasConcept C4554734 @default.
- W4385647457 hasConcept C55493867 @default.
- W4385647457 hasConcept C63479239 @default.
- W4385647457 hasConcept C96711827 @default.
- W4385647457 hasConceptScore W4385647457C104317684 @default.
- W4385647457 hasConceptScore W4385647457C111919701 @default.
- W4385647457 hasConceptScore W4385647457C119857082 @default.
- W4385647457 hasConceptScore W4385647457C13280743 @default.
- W4385647457 hasConceptScore W4385647457C134306372 @default.
- W4385647457 hasConceptScore W4385647457C153083717 @default.
- W4385647457 hasConceptScore W4385647457C154945302 @default.
- W4385647457 hasConceptScore W4385647457C162324750 @default.
- W4385647457 hasConceptScore W4385647457C177148314 @default.
- W4385647457 hasConceptScore W4385647457C185592680 @default.
- W4385647457 hasConceptScore W4385647457C185798385 @default.
- W4385647457 hasConceptScore W4385647457C187736073 @default.
- W4385647457 hasConceptScore W4385647457C204321447 @default.
- W4385647457 hasConceptScore W4385647457C205649164 @default.
- W4385647457 hasConceptScore W4385647457C2776145971 @default.
- W4385647457 hasConceptScore W4385647457C2776321320 @default.
- W4385647457 hasConceptScore W4385647457C2779135771 @default.
- W4385647457 hasConceptScore W4385647457C2780451532 @default.
- W4385647457 hasConceptScore W4385647457C33923547 @default.
- W4385647457 hasConceptScore W4385647457C41008148 @default.
- W4385647457 hasConceptScore W4385647457C43126263 @default.
- W4385647457 hasConceptScore W4385647457C4554734 @default.
- W4385647457 hasConceptScore W4385647457C55493867 @default.
- W4385647457 hasConceptScore W4385647457C63479239 @default.
- W4385647457 hasConceptScore W4385647457C96711827 @default.
- W4385647457 hasFunder F4320321001 @default.
- W4385647457 hasIssue "8" @default.
- W4385647457 hasLocation W43856474571 @default.
- W4385647457 hasLocation W43856474572 @default.
- W4385647457 hasOpenAccess W4385647457 @default.
- W4385647457 hasPrimaryLocation W43856474571 @default.
- W4385647457 hasRelatedWork W1980748319 @default.
- W4385647457 hasRelatedWork W2146948107 @default.
- W4385647457 hasRelatedWork W2405038964 @default.
- W4385647457 hasRelatedWork W2952732525 @default.
- W4385647457 hasRelatedWork W3031263788 @default.
- W4385647457 hasRelatedWork W3101260801 @default.
- W4385647457 hasRelatedWork W3156268002 @default.
- W4385647457 hasRelatedWork W3214642209 @default.
- W4385647457 hasRelatedWork W4226048468 @default.
- W4385647457 hasRelatedWork W4308949089 @default.
- W4385647457 hasVolume "39" @default.
- W4385647457 isParatext "false" @default.
- W4385647457 isRetracted "false" @default.
- W4385647457 workType "article" @default.